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

    Neuronpedia

    INDEX
    Explanations

    advice or verification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    বাত
    0.38
    usermodel
    0.36
    了一个
    0.36
    ({"
    0.35
    RelativeLayout
    0.35
    Characteristic
    0.34
    didReceive
    0.34
    ToString
    0.33
    Electronic
    0.33
    password
    0.33
    POSITIVE LOGITS
     queste
    0.43
     Queste
    0.42
     les
    0.40
     failings
    0.40
     hérit
    0.40
     इनमें
    0.39
     desses
    0.39
     THESE
    0.38
     estos
    0.38
     nantinya
    0.38
    Act Density 0.625%

    No Known Activations