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

    Neuronpedia

    INDEX
    Explanations

    aco

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     McCl
    -0.07
    و
    -0.07
     ως
    -0.06
    geh
    -0.06
    _probs
    -0.06
     представляет
    -0.06
    ょう
    -0.06
    .DialogResult
    -0.06
     груп
    -0.06
    (ph
    -0.06
    POSITIVE LOGITS
    rch
    0.08
     ENG
    0.07
     hóa
    0.06
     bas
    0.06
     ettik
    0.06
     Levine
    0.06
     direkt
    0.06
    طة
    0.06
     '/'↵
    0.06
     (*((
    0.06
    Act Density 0.000%

    No Known Activations