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

    Neuronpedia

    INDEX
    Explanations

    created by the Gemma team

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Myers
    0.48
     Ap
    0.47
     Myers
    0.46
     ap
    0.46
    Ap
    0.45
     AP
    0.44
     Raj
    0.43
    रेज
    0.42
    Raj
    0.42
    AP
    0.41
    POSITIVE LOGITS
    ம்ம
    0.39
     झ
    0.38
    lop
    0.35
     Nervous
    0.35
    hu
    0.35
    gF
    0.35
    宦
    0.34
     juniper
    0.34
     Loyalty
    0.33
    ionage
    0.32
    Act Density 0.016%

    No Known Activations