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

    Neuronpedia

    INDEX
    Explanations

    Sports records

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sın
    -0.07
     elic
    -0.07
    ـ
    -0.06
     contrad
    -0.06
     Ik
    -0.06
    _clr
    -0.06
     Ler
    -0.06
     practise
    -0.06
    ــ
    -0.05
     fikir
    -0.05
    POSITIVE LOGITS
    ands
    0.07
    ?,
    0.06
    (Point
    0.06
     Dietary
    0.06
    Org
    0.06
    .Name
    0.06
     ↵↵
    0.06
    领导
    0.06
    .Modified
    0.06
     suspected
    0.06
    Act Density 0.018%

    No Known Activations