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

    Neuronpedia

    INDEX
    Explanations

    say "Category"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    save
    -0.07
     perc
    -0.07
     prosperity
    -0.07
    震动
    -0.07
    $error
    -0.07
     aktiv
    -0.06
     psychologists
    -0.06
    (save
    -0.06
    一键
    -0.06
     التون
    -0.06
    POSITIVE LOGITS
    OMPI
    0.07
     gross
    0.07
    果园
    0.07
    Lik
    0.07
    읊
    0.06
    薄
    0.06
    Ὃ
    0.06
    车展
    0.06
    slaught
    0.06
    ("(
    0.06
    Act Density 0.013%

    No Known Activations