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

    Neuronpedia

    INDEX
    Explanations

    authentication

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    坡
    -0.08
    亲戚
    -0.07
    ษา
    -0.07
    _map
    -0.07
    绕
    -0.07
     Irene
    -0.07
    _POS
    -0.07
    _area
    -0.07
     באי
    -0.07
    .”↵
    -0.07
    POSITIVE LOGITS
    ,
    0.10
     prosecution
    0.08
    ，
    0.08
     "=",
    0.07
    legs
    0.07
    ,['
    0.07
    ieux
    0.07
    汫
    0.07
    asename
    0.07
    ᵧ
    0.07
    Act Density 0.014%

    No Known Activations