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

    Neuronpedia

    INDEX
    Explanations

    names and classifications of plant species

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

    after names or codes

    np_acts-logits-general · gemini-2.0-flash

    word fragments followed by continuations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     houſe
    -0.95
     itſelf
    -0.90
     Houſe
    -0.85
     EnglishChoose
    -0.85
     perſon
    -0.83
     ſever
    -0.83
     Ory
    -0.81
     poffible
    -0.80
     iſt
    -0.79
     themſelves
    -0.78
    POSITIVE LOGITS
     ‘
    0.67
     B
    0.64
     K
    0.64
     V
    0.62
     '
    0.62
     Y
    0.62
     S
    0.61
     D
    0.61
     G
    0.60
    來的
    0.58
    Act Density 0.725%

    No Known Activations