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

    Neuronpedia

    INDEX
    Explanations

    Old normal evolution value ponder

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     наука
    0.46
     गेहूं
    0.43
     townships
    0.41
     Forth
    0.40
     Directories
    0.40
     tae
    0.39
    ウェブ
    0.39
     Calf
    0.39
    ரைப்
    0.39
     oaths
    0.38
    POSITIVE LOGITS
    pr
    0.50
    if
    0.49
    BIT
    0.45
    oli
    0.43
    bit
    0.42
    of
    0.41
    Time
    0.40
    TIMESTAMP
    0.39
    ari
    0.39
    orski
    0.39
    Act Density 0.000%

    No Known Activations