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

    Neuronpedia

    INDEX
    Explanations

    purveyor of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     parecía
    0.86
     mutta
    0.81
     endophytic
    0.75
     genocide
    0.75
     embol
    0.74
     maar
    0.73
     när
    0.73
     siente
    0.73
     negara
    0.72
    が含ま
    0.72
    POSITIVE LOGITS
    J
    1.19
     PRICES
    0.97
     J
    0.95
     HOTEL
    0.91
    W
    0.91
    ANY
    0.88
    HAR
    0.88
     Wm
    0.86
     R
    0.86
    EL
    0.86
    Act Density 0.025%

    No Known Activations