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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Note
    -0.07
    pcf
    -0.07
    -mf
    -0.06
    thal
    -0.06
    otp
    -0.06
    Nb
    -0.06
     fetched
    -0.06
    _match
    -0.06
     Version
    -0.06
    影響
    -0.06
    POSITIVE LOGITS
     he
    0.07
    สก
    0.07
    ρι
    0.07
     they
    0.06
     she
    0.06
    =""↵
    0.06
    ammers
    0.06
     disagree
    0.06
    (Const
    0.06
     verbally
    0.06
    Act Density 0.013%

    No Known Activations