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

    Neuronpedia

    INDEX
    Explanations

    generally

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ط
    0.50
    Л
    0.48
    И
    0.47
    ES
    0.46
     wilderness
    0.46
    В
    0.46
    ನ
    0.45
    У
    0.45
    та
    0.43
     اړه
    0.43
    POSITIVE LOGITS
    ImageQueue
    0.50
     bào
    0.50
    ｄ
    0.50
     tembok
    0.49
    nilvadipine
    0.49
     pInBuffer
    0.49
    arantad
    0.49
     coefficient
    0.47
     coeff
    0.47
    ąd
    0.47
    Act Density 0.003%

    No Known Activations