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

    Neuronpedia

    INDEX
    Explanations

    deflation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ASIC
    -0.08
    _tar
    -0.07
    -positive
    -0.06
    :@"%@
    -0.06
    標
    -0.06
    نسي
    -0.06
    ;(
    -0.06
     pickup
    -0.06
     roadway
    -0.06
     reminded
    -0.06
    POSITIVE LOGITS
     הגוף
    0.08
    明智
    0.07
     første
    0.07
     severe
    0.07
    觉
    0.06
    ᆼ
    0.06
    hyper
    0.06
    なら
    0.06
    저
    0.06
    ภาพ
    0.06
    Act Density 0.001%

    No Known Activations