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

    Neuronpedia

    INDEX
    Explanations

    Asian languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    command
    -0.07
     Ir
    -0.07
     factura
    -0.06
     العظ
    -0.06
    (dtype
    -0.06
    lng
    -0.06
    الص
    -0.06
     şiddet
    -0.06
     procession
    -0.06
     عقد
    -0.06
    POSITIVE LOGITS
    _window
    0.07
    Fs
    0.07
    William
    0.07
    _processes
    0.07
    ())[
    0.07
    verb
    0.06
     subrange
    0.06
    ><
    0.06
     morality
    0.06
    SetName
    0.06
    Act Density 0.020%

    No Known Activations