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

    Neuronpedia

    INDEX
    Explanations

    numeric or hexadecimal values

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

    numbers and hex values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.48
     Vite
    -0.41
    uppe
    -0.41
     aide
    -0.41
    ❸
    -0.40
     McIntyre
    -0.39
    MessageOf
    -0.38
     Gier
    -0.37
    VII
    -0.36
    ivi
    -0.36
    POSITIVE LOGITS
     feroit
    0.69
    出版年
    0.67
     pouvoit
    0.62
     auroit
    0.57
    IntoConstraints
    0.56
    retudo
    0.56
     ainfi
    0.56
    /**
    0.53
     nastro
    0.53
     habet
    0.53
    Act Density 0.039%

    No Known Activations