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

    Neuronpedia

    INDEX
    Explanations

    beginning of lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     whole
    0.43
    gradation
    0.37
     entirety
    0.35
    estimator
    0.34
    drying
    0.34
     compression
    0.33
     surprisingly
    0.33
    eliness
    0.33
     وړاندوینې
    0.32
     unarmed
    0.32
    POSITIVE LOGITS
    ***
    0.56
    WARNING
    0.56
     BEGIN
    0.55
     ===
    0.53
     ***
    0.52
     THIS
    0.52
    inizio
    0.52
    нимание
    0.52
     ==
    0.51
    ====
    0.51
    Act Density 0.024%

    No Known Activations