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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AAD
    -0.07
    _sort
    -0.06
    AREA
    -0.06
    insn
    -0.06
    utan
    -0.06
    .POS
    -0.06
    934
    -0.06
    (chip
    -0.06
    ステ
    -0.06
    unload
    -0.06
    POSITIVE LOGITS
     henüz
    0.07
     exacerbated
    0.06
     zda
    0.06
    引用
    0.06
     moistur
    0.06
    lenmesi
    0.06
     Univers
    0.06
    versed
    0.06
     khuẩn
    0.06
     devoid
    0.06
    Act Density 0.036%

    No Known Activations