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

    Neuronpedia

    INDEX
    Explanations

    anaerobic environments and canals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    1.16
    r
    1.13
    il
    0.98
    ر
    0.92
    n
    0.89
    k
    0.87
    ar
    0.84
    nya
    0.84
    d
    0.79
    y
    0.76
    POSITIVE LOGITS
    BS
    0.77
    Ν
    0.63
    ટ
    0.59
     indiquer
    0.58
    ッチン
    0.57
    ว้
    0.57
    IGHT
    0.56
    Scheduled
    0.56
    邗
    0.56
    abban
    0.56
    Act Density 0.001%

    No Known Activations