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

    Neuronpedia

    INDEX
    Explanations

    store for or within

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     IDs
    0.70
    ា
    0.70
    zäh
    0.69
     A
    0.66
     &_
    0.63
    al
    0.62
    بي
    0.62
     OMG
    0.61
    كل
    0.60
    ku
    0.59
    POSITIVE LOGITS
    s
    1.16
    ی
    1.15
    ς
    0.92
    polynomial
    0.80
    ים
    0.74
    solution
    0.74
     recording
    0.73
    ם
    0.72
    question
    0.71
    Equations
    0.71
    Act Density 0.000%

    No Known Activations