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

    Neuronpedia

    INDEX
    Explanations

    ===========

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /types
    -0.08
    -equipped
    -0.07
    Έ
    -0.07
    جبهة
    -0.07
    .Z
    -0.07
    GY
    -0.07
     ALS
    -0.07
    Ā
    -0.07
     canv
    -0.06
    aqu
    -0.06
    POSITIVE LOGITS
    可靠
    0.08
    uliar
    0.08
     Calls
    0.08
     lexer
    0.07
     Signature
    0.07
    users
    0.07
     contrôle
    0.07
     similarity
    0.07
    دخ
    0.07
    _BAD
    0.07
    Act Density 0.000%

    No Known Activations