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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    和技术
    -0.07
     شب
    -0.07
     Storage
    -0.06
     Often
    -0.06
    developers
    -0.06
    旋转
    -0.06
     Ownership
    -0.06
    作为一种
    -0.06
    𝙻
    -0.06
    Spanish
    -0.06
    POSITIVE LOGITS
    낀
    0.07
    论述
    0.07
    在乎
    0.07
    '");↵
    0.07
     shortcomings
    0.07
    ;↵
    0.07
    .share
    0.06
    !!↵
    0.06
     yabancı
    0.06
    iggs
    0.06
    Act Density 0.152%

    No Known Activations