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

    Neuronpedia

    INDEX
    Explanations

    same

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Giants
    -0.08
     samozřejmě
    -0.07
    ten
    -0.07
    vas
    -0.07
    ằ
    -0.06
    "){
    -0.06
    aeper
    -0.06
    一
    -0.06
    قیق
    -0.06
    continued
    -0.06
    POSITIVE LOGITS
     strokeLine
    0.06
    _ble
    0.06
     sis
    0.06
     SSL
    0.06
     consenting
    0.06
    _logo
    0.06
    Hist
    0.06
     виды
    0.06
    _SENT
    0.06
     $.
    0.06
    Act Density 0.032%

    No Known Activations