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

    Neuronpedia

    INDEX
    Explanations

    if macroscopic and object

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    avali
    0.45
     अ
    0.45
     кори
    0.42
    focus
    0.42
     simpler
    0.42
     False
    0.40
    common
    0.40
    cors
    0.40
    icing
    0.39
    $$
    0.39
    POSITIVE LOGITS
    支払い
    0.51
    窰
    0.49
    ע
    0.49
    逺
    0.48
     высоте
    0.47
    ש
    0.46
    उँ
    0.46
    ह्न
    0.46
    ]]]]
    0.46
    τοι
    0.45
    Act Density 0.003%

    No Known Activations