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

    Neuronpedia

    INDEX
    Explanations

    parentheses, brackets, and code formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    í
    0.59
    ö
    0.54
    i
    0.52
    ка
    0.49
    ium
    0.48
    um
    0.47
    ön
    0.46
    Connections
    0.46
    тен
    0.46
    ="
    0.46
    POSITIVE LOGITS
     võivad
    0.52
     doivent
    0.49
     അപകട
    0.48
     dovr
    0.48
     prépuce
    0.48
     ordnance
    0.47
    িলম্বে
    0.47
     moteurs
    0.47
     électriques
    0.46
     ɖ
    0.46
    Act Density 0.002%

    No Known Activations