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

    Neuronpedia

    INDEX
    Explanations

    dimensional

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     allergies
    -0.07
     toss
    -0.07
    ة
    -0.07
    uz
    -0.07
     Other
    -0.07
     vicious
    -0.07
     Blob
    -0.07
    First
    -0.06
     bus
    -0.06
     STOP
    -0.06
    POSITIVE LOGITS
     طول
    0.06
     ακ
    0.06
    εδ
    0.06
     Schw
    0.06
    rocessing
    0.06
    builtin
    0.06
     Lum
    0.06
    _TRAN
    0.06
     захоп
    0.06
    /stretchr
    0.06
    Act Density 0.011%

    No Known Activations