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

    Neuronpedia

    INDEX
    Explanations

    code and configuration files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    isinden
    -0.07
     hostile
    -0.06
    .writerow
    -0.06
    ukes
    -0.06
    urm
    -0.06
    filt
    -0.06
    ůj
    -0.06
    ,application
    -0.06
    ďte
    -0.06
     owl
    -0.06
    POSITIVE LOGITS
    -g
    0.06
     صنع
    0.06
    <Select
    0.06
    ينية
    0.06
    (gameObject
    0.06
    /story
    0.06
     DFA
    0.06
     persuade
    0.06
    YNC
    0.06
     Defaults
    0.06
    Act Density 0.015%

    No Known Activations