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

    Neuronpedia

    INDEX
    Explanations

    code and ethical boundaries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ê
    0.54
    ę
    0.53
    expérience
    0.52
    À
    0.52
    המ
    0.51
    Ак
    0.50
    Contra
    0.50
    दूसरे
    0.50
     résoudre
    0.50
    சிற
    0.49
    POSITIVE LOGITS
    ,
    0.49
     seedling
    0.47
    批
    0.46
     agglut
    0.46
     cadence
    0.46
     as
    0.46
    ive
    0.46
     isolation
    0.46
     chaff
    0.45
     enlightenment
    0.45
    Act Density 0.000%

    No Known Activations