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

    Neuronpedia

    INDEX
    Explanations

    say numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     firsthand
    -0.07
    uci
    -0.07
     Feet
    -0.07
    ze
    -0.06
     счита
    -0.06
    (lbl
    -0.06
     одном
    -0.06
    ssize
    -0.06
    Fantastic
    -0.06
    カードローン
    -0.06
    POSITIVE LOGITS
    替代
    0.07
    _reporting
    0.07
    굅
    0.07
    拱
    0.07
    =[↵
    0.07
    ******
↵
    0.07
    ','');↵
    0.06
     returns
    0.06
    textBox
    0.06
    elp
    0.06
    Act Density 0.026%

    No Known Activations