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

    Neuronpedia

    INDEX
    Explanations

    capabilities or possibilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sequent
    0.56
    検討
    0.51
    odet
    0.51
    renergic
    0.50
    doctoral
    0.49
    ش
    0.49
    packaged
    0.48
    study
    0.46
    احث
    0.46
    di
    0.46
    POSITIVE LOGITS
     MAY
    0.52
     นาง
    0.46
     😊
    0.46
     COULD
    0.46
     bellissimo
    0.46
     Puoi
    0.44
     tanh
    0.44
     patted
    0.43
     manages
    0.43
     tram
    0.43
    Act Density 0.001%

    No Known Activations