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

    Neuronpedia

    INDEX
    Explanations

    parsing expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Worm
    -0.09
    -reset
    -0.09
     Gesundheit
    -0.08
    .Reset
    -0.08
    -view
    -0.08
     RESET
    -0.08
    Ẩ
    -0.08
     peste
    -0.08
     års
    -0.08
     Reset
    -0.08
    POSITIVE LOGITS
    oplayer
    0.08
    หย
    0.08
    (value
    0.08
    오
    0.08
     значение
    0.08
    _LITERAL
    0.08
     speeches
    0.07
     opa
    0.07
     blob
    0.07
    (token
    0.07
    Act Density 0.005%

    No Known Activations