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

    Neuronpedia

    INDEX
    Explanations

    articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    andır
    -0.07
    chas
    -0.07
     @{@"
    -0.06
    .Click
    -0.06
     JNI
    -0.06
     SEXP
    -0.06
    GetValue
    -0.06
     Lists
    -0.06
    oğu
    -0.06
     cref
    -0.06
    POSITIVE LOGITS
     specifies
    0.07
    +f
    0.06
     ladies
    0.06
     maintain
    0.06
    [$
    0.06
     харч
    0.06
     aggreg
    0.06
    ！」
    0.06
    406
    0.06
    EAR
    0.06
    Act Density 0.023%

    No Known Activations