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

    Neuronpedia

    INDEX
    Explanations

    enough

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -il
    -0.07
    -di
    -0.06
    ategory
    -0.06
    プロ
    -0.06
     lda
    -0.06
    uş
    -0.06
     KAR
    -0.06
     slou
    -0.06
    di
    -0.06
     vin
    -0.06
    POSITIVE LOGITS
     pitch
    0.07
    _Type
    0.07
    Anime
    0.07
     hints
    0.07
    capability
    0.06
     ascend
    0.06
    層
    0.06
    -away
    0.06
    xEF
    0.06
    .firstChild
    0.06
    Act Density 0.006%

    No Known Activations