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

    Neuronpedia

    INDEX
    Explanations

    asking for information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ever
    0.57
    el
    0.56
    ong
    0.52
    ine
    0.50
    berg
    0.49
    ess
    0.49
    are
    0.49
    í
    0.49
    letter
    0.48
    active
    0.47
    POSITIVE LOGITS
     *}\
    0.54
     adherents
    0.53
     turnovers
    0.49
     هناك
    0.48
    ॰ऍ
    0.48
     hike
    0.47
     GoObject
    0.46
     getText
    0.46
    НА
    0.45
     jt
    0.45
    Act Density 0.001%

    No Known Activations