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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Transport
    -0.07
    媓
    -0.07
     fibonacci
    -0.07
    疔
    -0.07
    �
    -0.07
     ingres
    -0.07
    抿
    -0.06
     PED
    -0.06
     Fibonacci
    -0.06
     Rh
    -0.06
    POSITIVE LOGITS
    cran
    0.08
     unveiled
    0.07
    claim
    0.07
    プロジェクト
    0.07
    ками
    0.07
     kernel
    0.07
    ernel
    0.07
     Scal
    0.07
    혔
    0.07
     *))
    0.07
    Act Density 0.001%

    No Known Activations