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

    Neuronpedia

    INDEX
    Explanations

    impairment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IFEST
    -0.08
    🐑
    -0.07
    .net
    -0.07
    /weather
    -0.07
     Drake
    -0.07
    _CLOCK
    -0.07
    twenty
    -0.07
    .receive
    -0.07
    থ
    -0.07
     medios
    -0.07
    POSITIVE LOGITS
    utivo
    0.07
     العراق
    0.07
    댄
    0.07
    护身符
    0.07
     Marxist
    0.07
    行為
    0.06
     \|
    0.06
     Lumpur
    0.06
    .DateField
    0.06
     Trailer
    0.06
    Act Density 0.005%

    No Known Activations