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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    TO
    -0.08
     методи
    -0.07
     to
    -0.07
     intimacy
    -0.07
     weeks
    -0.07
     cultures
    -0.07
    Bars
    -0.07
     indicate
    -0.07
     with
    -0.07
    probe
    -0.07
    POSITIVE LOGITS
    _PAYLOAD
    0.07
    Falsy
    0.07
    .kode
    0.06
    OfWeek
    0.06
    .ONE
    0.06
    Ω
    0.06
    (isinstance
    0.06
    UFACT
    0.06
     Adolf
    0.06
    \/
    0.06
    Act Density 0.329%

    No Known Activations