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

    Neuronpedia

    INDEX
    Explanations

    instances of verbs, especially when followed by "to" or "be".

    oai_token-act-pair · gemini-2.0-flash

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Efq
    -1.01
     صوتيه
    -1.01
     houſe
    -0.96
     Majefty
    -0.95
     Theſe
    -0.93
     Houſe
    -0.90
     يتيمه
    -0.90
    ſelf
    -0.90
     purpoſe
    -0.88
     myſelf
    -0.87
    POSITIVE LOGITS
     NUnit
    0.55
     have
    0.54
     correct
    0.48
    abá
    0.45
     take
    0.43
     can
    0.43
    akesh
    0.42
     s
    0.42
     stand
    0.41
     see
    0.40
    Act Density 2.088%

    No Known Activations