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

    Neuronpedia

    INDEX
    Explanations

    unit conversions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ิสต
    -0.07
    ิโ
    -0.07
     stav
    -0.07
    _invalid
    -0.06
     dolls
    -0.06
     تمر
    -0.06
     spree
    -0.06
    editar
    -0.06
    $email
    -0.06
    -reader
    -0.06
    POSITIVE LOGITS
     SCI
    0.07
    hape
    0.06
     anc
    0.06
    CATEGORY
    0.06
     XXX
    0.06
     ro
    0.06
    >f
    0.06
    اهش
    0.06
    ;-
    0.06
     ORD
    0.06
    Act Density 0.142%

    No Known Activations