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

    Neuronpedia

    INDEX
    Explanations

    following comma optional

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uminous
    0.40
    じる
    0.37
    olf
    0.37
    ymmetry
    0.36
    uez
    0.36
    chemic
    0.36
     типу
    0.36
     দেবী
    0.36
    issa
    0.35
    驶
    0.35
    POSITIVE LOGITS
     povos
    0.46
     exagger
    0.45
     فبراير
    0.45
    猊
    0.43
     afro
    0.43
     punten
    0.42
    Cash
    0.42
     apathy
    0.42
    teeth
    0.42
     ord
    0.41
    Act Density 0.001%

    No Known Activations