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

    Neuronpedia

    INDEX
    Explanations

    acts as a gateway

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     सहायता
    0.42
    saveTool
    0.42
    աց
    0.41
    퐫
    0.41
     Gig
    0.39
     মাটি
    0.39
    OnFileChange
    0.38
     футболдук
    0.38
     دائو
    0.38
    RetResult
    0.38
    POSITIVE LOGITS
    °.
    0.40
     praises
    0.38
    忻
    0.37
    ahl
    0.37
    riches
    0.37
    ．
    0.37
    °
    0.36
    imming
    0.36
    i
    0.35
    بال
    0.35
    Act Density 0.010%

    No Known Activations