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

    Neuronpedia

    INDEX
    Explanations

    parental control restrictions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ad
    0.47
    Ori
    0.46
    Assim
    0.46
    2
    0.44
    Inc
    0.44
    Information
    0.43
    De
    0.42
    zeta
    0.42
    Integr
    0.42
    Radi
    0.41
    POSITIVE LOGITS
    尣
    0.50
     हिस्
    0.45
    piegel
    0.44
     регули
    0.43
    ాల్లో
    0.43
     اهم
    0.43
     quản
    0.43
     ヘ
    0.43
    isLen
    0.42
     режим
    0.41
    Act Density 0.007%

    No Known Activations