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

    Neuronpedia

    INDEX
    Explanations

    boolean logic/code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     singly
    -0.07
     iki
    -0.06
    Digit
    -0.06
     Mas
    -0.06
     produced
    -0.06
    ningen
    -0.06
    kins
    -0.06
    ----↵
    -0.06
    ี้↵
    -0.06
     uniq
    -0.06
    POSITIVE LOGITS
    ‌شده
    0.06
    national
    0.06
    edido
    0.06
    :black
    0.06
    .PLAIN
    0.06
    ลอง
    0.06
    Це
    0.06
     CHECK
    0.06
    _Right
    0.06
     apartheid
    0.06
    Act Density 0.092%

    No Known Activations