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

    Neuronpedia

    INDEX
    Explanations

    Questions in dialog

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fires
    -0.07
     Donetsk
    -0.06
    _playing
    -0.06
    سل
    -0.06
     Sequ
    -0.06
    .rotation
    -0.06
    PropTypes
    -0.06
    .Setter
    -0.06
    沉
    -0.06
     وس
    -0.05
    POSITIVE LOGITS
     ){
    0.07
    spect
    0.07
    merged
    0.06
     considerable
    0.06
     chtěl
    0.06
    ivated
    0.06
    McC
    0.06
    ряду
    0.06
     hourly
    0.06
    ουμε
    0.06
    Act Density 0.028%

    No Known Activations