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

    Neuronpedia

    INDEX
    Explanations

    use their head

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Can
    0.47
     Be
    0.43
     del
    0.41
     Fuller
    0.39
     Fo
    0.39
     espon
    0.39
     ANI
    0.38
     eyes
    0.38
     psich
    0.37
    correspond
    0.37
    POSITIVE LOGITS
    postdata
    0.39
    কমার্স
    0.38
     nari
    0.38
     пово
    0.37
    ဋ
    0.37
    Hig
    0.36
    សូម
    0.34
    @-
    0.34
    पट
    0.34
     पनि
    0.34
    Act Density 0.024%

    No Known Activations