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

    Neuronpedia

    INDEX
    Explanations

    company or variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    د
    0.93
    л
    0.91
    ם
    0.86
     alleys
    0.82
     blinds
    0.77
     bungalows
    0.77
    」。
    0.75
    лм
    0.74
     inhale
    0.74
     cultivos
    0.73
    POSITIVE LOGITS
    5
    1.20
    3
    1.19
    ing
    1.18
    1
    1.09
    4
    1.05
    した
    1.01
    I
    1.00
    6
    0.98
    ła
    0.97
    Company
    0.93
    Act Density 0.000%

    No Known Activations