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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Align
    -0.07
    Attrib
    -0.07
     Elim
    -0.07
     perfection
    -0.06
     gobierno
    -0.06
     topic
    -0.06
     overl
    -0.06
    rete
    -0.06
    Day
    -0.06
    casecmp
    -0.06
    POSITIVE LOGITS
    انیا
    0.06
     Cedar
    0.06
     adopting
    0.06
    .inner
    0.06
    )){↵
    0.06
     rund
    0.06
    destruct
    0.06
    یین
    0.06
     Mediterranean
    0.06
    _encoding
    0.06
    Act Density 0.064%

    No Known Activations