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

    Neuronpedia

    INDEX
    Explanations

    file name or number assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    炵
    0.43
    निम
    0.41
     Pandemic
    0.40
     keywords
    0.40
     klik
    0.40
     photometry
    0.40
    คลิ
    0.40
     Hits
    0.39
     sărb
    0.39
    0.39
    POSITIVE LOGITS
    ing
    0.50
    shaded
    0.46
    bc
    0.44
    fontein
    0.44
     ش
    0.42
    unset
    0.42
    null
    0.41
    d
    0.41
    ité
    0.41
    sch
    0.41
    Act Density 0.001%

    No Known Activations