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

    Neuronpedia

    INDEX
    Explanations

    fresh

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    abant
    -0.07
    女性
    -0.07
    upid
    -0.07
     Lib
    -0.06
     ATT
    -0.06
     هذه
    -0.06
     Geoffrey
    -0.06
     enumerated
    -0.06
     Deposit
    -0.06
    ToBounds
    -0.06
    POSITIVE LOGITS
     fresh
    0.07
     pam
    0.07
    READY
    0.07
     Fresh
    0.07
    Tôi
    0.06
    ylan
    0.06
     finde
    0.06
     kesin
    0.06
    .fname
    0.06
    ([
↵
    0.06
    Act Density 0.004%

    No Known Activations