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

    Neuronpedia

    INDEX
    Explanations

    explaining why or difficulties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     scour
    0.40
    вість
    0.38
     महम
    0.38
    പാട്
    0.38
     dominion
    0.37
     priv
    0.37
    ധിപ
    0.36
    pInBuffer
    0.36
     lộ
    0.35
     Sindh
    0.35
    POSITIVE LOGITS
    Pattern
    0.41
     Pattern
    0.40
    itale
    0.39
    Rec
    0.39
    )$;
    0.39
    agement
    0.38
    设
    0.37
    Meta
    0.37
     rask
    0.37
     στά
    0.37
    Act Density 0.000%

    No Known Activations