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

    Neuronpedia

    INDEX
    Explanations

    promises and guarantees

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    $}
    1.53
     acidosis
    1.53
     rosto
    1.48
     sunken
    1.45
     ihop
    1.45
     agreg
    1.45
    ంలో
    1.44
     acquitted
    1.42
    ول
    1.40
    setForeground
    1.40
    POSITIVE LOGITS
    ي
    2.27
    ä
    2.13
    ি
    1.73
    ри
    1.70
    𝗶
    1.70
    ون
    1.66
    ں
    1.64
    et
    1.61
    y
    1.60
    в
    1.59
    Act Density 0.026%

    No Known Activations