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

    Neuronpedia

    INDEX
    Explanations

    say .net

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -"
    -0.07
     male
    -0.07
    清净
    -0.07
    ricing
    -0.07
     lateral
    -0.07
     delicate
    -0.07
     Gol
    -0.07
    𝚊
    -0.07
    陆
    -0.06
    .languages
    -0.06
    POSITIVE LOGITS
     milfs
    0.07
    🔪
    0.07
    سف
    0.07
    ствие
    0.07
    ChangedEventArgs
    0.07
    訪
    0.07
    invalid
    0.06
    おります
    0.06
    ство
    0.06
     Orig
    0.06
    Act Density 0.000%

    No Known Activations