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

    Neuronpedia

    INDEX
    Explanations

    finding information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <T
    -0.07
     мяс
    -0.06
    BUILD
    -0.06
    ох
    -0.06
     focused
    -0.06
    вин
    -0.06
     monuments
    -0.06
     fug
    -0.06
    (filepath
    -0.06
     confl
    -0.06
    POSITIVE LOGITS
     originate
    0.07
     معن
    0.06
     elo
    0.06
     nam
    0.06
     unrestricted
    0.06
     그냥
    0.06
    _OM
    0.06
     temperatura
    0.06
    .son
    0.06
    regon
    0.06
    Act Density 0.039%

    No Known Activations