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

    Neuronpedia

    INDEX
    Explanations

    code and labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cccnc
    0.46
     স্থলে
    0.46
     jTextField
    0.45
    jTextField
    0.45
    jButton
    0.42
     jButton
    0.41
    蠶
    0.41
     MNR
    0.40
    ensa
    0.40
    ષ્ણા
    0.40
    POSITIVE LOGITS
     svg
    0.38
    =
    0.38
    ws
    0.37
     μπο
    0.37
    ={
    0.37
    给定
    0.36
    '],
    0.36
     কোলে
    0.35
     coincidence
    0.35
     brushed
    0.35
    Act Density 0.000%

    No Known Activations