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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating technology and advancements

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

    frequently followed by evaluative adjectives

    np_acts-logits-general · gemini-2.0-flash

    really importanta lot ofreally badgreat example

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EndContext
    -0.33
     собой
    -0.32
     DE
    -0.31
     de
    -0.31
     위해
    -0.31
     AD
    -0.29
     En
    -0.28
     TJ
    -0.28
     SAC
    -0.28
     dirigir
    -0.28
    POSITIVE LOGITS
    onViewCreated
    0.71
    viewDidLoad
    0.69
     WaitForSeconds
    0.63
    windowFixed
    0.62
     ſind
    0.62
     queſta
    0.61
    posedge
    0.61
    Filmographie
    0.59
     increí
    0.58
    ymce
    0.57
    Act Density 0.926%

    No Known Activations