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

    Neuronpedia

    INDEX
    Explanations

    Non-English text/code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Adv
    -0.07
     Ghost
    -0.06
     additive
    -0.06
    (opt
    -0.06
     pragmatic
    -0.06
    ninger
    -0.06
    nt
    -0.06
     tersebut
    -0.06
     ragazze
    -0.06
    di
    -0.06
    POSITIVE LOGITS
    xmlns
    0.08
    stackpath
    0.07
    /graphql
    0.07
     стак
    0.06
    егор
    0.06
    _EXEC
    0.06
    QUOTE
    0.06
    (hdc
    0.06
    fillable
    0.06
     carga
    0.06
    Act Density 0.471%

    No Known Activations