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

    Neuronpedia

    INDEX
    Explanations

    Arrays in code contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     immersed
    0.44
    0.41
    вер
    0.39
     Extern
    0.39
    Extern
    0.39
    warna
    0.38
     sprung
    0.37
     داده
    0.37
     immers
    0.36
    maal
    0.36
    POSITIVE LOGITS
     caráter
    0.38
    indication
    0.37
    preset
    0.36
    érance
    0.36
    除去
    0.36
     तेंदुआ
    0.35
     मरा
    0.35
     preservation
    0.34
     *>
    0.34
    hock
    0.34
    Act Density 0.000%

    No Known Activations