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

    Neuronpedia

    INDEX
    Explanations

    absolute prohibition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    坵
    0.49
    пати
    0.47
    รู
    0.46
    阏
    0.46
     kati
    0.45
    ደት
    0.43
    𒊒
    0.42
     arque
    0.42
    িয়েত
    0.42
     metodología
    0.42
    POSITIVE LOGITS
    0.43
     Illinois
    0.41
     E
    0.38
    ↵↵
    0.37
    /
    0.36
     B
    0.35
     '
    0.35
     Z
    0.34
     without
    0.34
     Loud
    0.34
    Act Density 0.000%

    No Known Activations