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

    Neuronpedia

    INDEX
    Explanations

    6-

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     built
    0.77
     using
    0.74
     automatically
    0.72
     always
    0.65
     construction
    0.65
     local
    0.65
     sanity
    0.64
     regulations
    0.64
     modules
    0.63
     electrical
    0.62
    POSITIVE LOGITS
    -(-
    0.87
    -
    0.74
    indungan
    0.74
    ENDING
    0.73
    ।-
    0.72
     pung
    0.72
    ־
    0.70
    Ending
    0.69
    -...
    0.69
    ـ
    0.68
    Act Density 0.140%

    No Known Activations