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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    EFI
    -0.07
    ournal
    -0.06
    ndx
    -0.06
    same
    -0.06
    none
    -0.06
    عان
    -0.06
    LINE
    -0.06
    .gif
    -0.06
    _network
    -0.06
    STD
    -0.06
    POSITIVE LOGITS
     outsiders
    0.07
     registered
    0.07
     Stranger
    0.07
     cooperate
    0.06
    $app
    0.06
     　　　　　　　　　　　
    0.06
    _epsilon
    0.06
    "){
↵
    0.06
     initially
    0.06
     Gonz
    0.06
    Act Density 0.006%

    No Known Activations