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

    Neuronpedia

    INDEX
    Explanations

    Russian text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .setBounds
    -0.06
    idders
    -0.06
    ोर
    -0.06
    _Dep
    -0.06
     Convenience
    -0.06
    ##
    -0.06
    WRAPPER
    -0.06
     entrada
    -0.06
     motivo
    -0.06
    _surface
    -0.06
    POSITIVE LOGITS
     الش
    0.07
     LGBT
    0.07
     облас
    0.07
     Slee
    0.06
     NL
    0.06
     Κυ
    0.06
    Ngh
    0.06
    .Where
    0.06
     Bloody
    0.06
    lds
    0.06
    Act Density 0.011%

    No Known Activations