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

    Neuronpedia

    INDEX
    Explanations

    operating system distributions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    $\--
    0.52
     кише
    0.52
    <0xAF>
    0.51
     −/−
    0.50
    jali
    0.50
    িংস
    0.48
     enthält
    0.48
     vodu
    0.47
    <0x9E>
    0.47
    螫
    0.47
    POSITIVE LOGITS
    Health
    0.50
    I
    0.49
    Gary
    0.48
     practicality
    0.47
     Health
    0.46
    Tic
    0.45
    P
    0.45
     Mental
    0.45
     a
    0.44
    B
    0.44
    Act Density 0.000%

    No Known Activations