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

    Neuronpedia

    INDEX
    Explanations

    poster

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ázaro
    -2.25
    釆
    -2.25
    rália
    -2.16
    糅
    -2.14
    籐
    -2.13
    estão
    -2.11
     समीक्षाएं
    -2.06
    ugais
    -2.06
     infamous
    -2.05
     solidly
    -2.03
    POSITIVE LOGITS
    a
    3.70
    e
    3.03
    an
    2.97
    ︲
    2.77
    er
    2.77
    9
    2.63
    龶
    2.45
    the
    2.42
    がんば
    2.41
    まさかの
    2.39
    Act Density 0.011%

    No Known Activations