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

    Neuronpedia

    INDEX
    Explanations

    Copyrighted publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    占地
    -0.07
    rowsable
    -0.07
    ƍ
    -0.07
     הודעה
    -0.06
    렧
    -0.06
    ’h
    -0.06
    迄今为止
    -0.06
    .pref
    -0.06
     тех
    -0.06
     gou
    -0.06
    POSITIVE LOGITS
    cpp
    0.07
     escalated
    0.07
    开心
    0.07
    |$
    0.07
    equal
    0.07
    绝不
    0.07
     }()↵
    0.07
    ế
    0.07
    =model
    0.07
    자가
    0.07
    Act Density 0.006%

    No Known Activations