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

    Neuronpedia

    INDEX
    Explanations

    responsible for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ד
    1.30
    Unable
    1.20
    marks
    1.20
    an
    1.18
     Sulph
    1.18
    μου
    1.17
    logout
    1.16
    র্থ
    1.16
    ſt
    1.15
    yf
    1.15
    POSITIVE LOGITS
     andar
    1.21
    ر
    1.17
     estes
    1.10
     lại
    1.10
     sehe
    1.07
    是一些
    1.06
     freeing
    1.05
     nồi
    1.02
    أ
    1.01
     ठहरा
    1.01
    Act Density 0.042%

    No Known Activations