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

    Neuronpedia

    INDEX
    Explanations

    lack of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     вниз
    0.84
    ୱ
    0.83
     Lizzie
    0.81
    ‍♀️
    0.80
     easing
    0.80
     со
    0.79
     underside
    0.77
     few
    0.76
    ‍♂️
    0.76
     buildTypes
    0.76
    POSITIVE LOGITS
     thereof
    1.32
    lust
    1.19
    sufficient
    1.18
    luster
    1.15
     sufficient
    1.12
    ative
    1.10
    access
    1.10
    athon
    1.09
     ausreiche
    1.05
     Sufficient
    1.04
    Act Density 0.017%

    No Known Activations