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

    Neuronpedia

    INDEX
    Explanations

    time intervals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ands
    -0.07
    <W
    -0.07
     theorists
    -0.07
     toxicity
    -0.07
     galaxy
    -0.07
    (cpu
    -0.06
    .Spec
    -0.06
     onError
    -0.06
     structured
    -0.06
     Thanks
    -0.06
    POSITIVE LOGITS
     disciplines
    0.07
    dana
    0.06
    ۲۵
    0.06
     compreh
    0.06
    das
    0.06
    embre
    0.06
     nit
    0.06
     corporations
    0.06
    olulu
    0.06
    멘
    0.06
    Act Density 0.020%

    No Known Activations