Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases that pertain to the concept of "first" or numerical rankings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    The token "First" or variants of it

    np_acts-logits-general · gemini-2.0-flash

    first followed by a noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lenker
    -0.64
     externi
    -0.63
    GraphicsUnit
    -0.55
    parsedMessage
    -0.55
    RetentionPolicy
    -0.55
     geldig
    -0.54
    각주
    -0.54
    astify
    -0.54
    disfraz
    -0.53
    Билгалдахарш
    -0.53
    POSITIVE LOGITS
     CreateTagHelper
    0.60
    apunov
    0.60
     Amendment
    0.53
    BufferException
    0.51
    paravant
    0.51
    bán
    0.51
     Responder
    0.51
    diq
    0.50
    impres
    0.50
    tisgarh
    0.49
    Act Density 0.151%

    No Known Activations