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

    Neuronpedia

    INDEX
    Explanations

    [@

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     school
    -0.07
    ♍
    -0.07
    ┭
    -0.07
     august
    -0.07
    신청
    -0.06
    ˳
    -0.06
    כור
    -0.06
    各单位
    -0.06
    xCD
    -0.06
    졍
    -0.06
    POSITIVE LOGITS
     staging
    0.07
     Andrea
    0.07
    -terrorism
    0.07
    erro
    0.07
    _target
    0.07
     digits
    0.06
    /db
    0.06
     חדר
    0.06
     amp
    0.06
    步伐
    0.06
    Act Density 0.012%

    No Known Activations