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

    Neuronpedia

    INDEX
    Explanations

    reading and sources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    verted
    0.42
    isNull
    0.42
     distinctions
    0.40
    Hist
    0.37
     historian
    0.36
     historians
    0.36
     hist
    0.36
     empty
    0.36
    iliar
    0.35
    empty
    0.35
    POSITIVE LOGITS
     đọc
    0.46
     읽
    0.46
     read
    0.46
     SOURCE
    0.42
     Spike
    0.41
     Read
    0.41
     सोर्स
    0.40
    读
    0.40
     jõ
    0.39
     Source
    0.39
    Act Density 0.001%

    No Known Activations