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

    Neuronpedia

    INDEX
    Explanations

    hour

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mand
    -0.07
    データ
    -0.07
    ัตน
    -0.07
     Satan
    -0.07
     cmp
    -0.07
    ñas
    -0.07
    nad
    -0.07
     transcend
    -0.06
     sabe
    -0.06
     sexdate
    -0.06
    POSITIVE LOGITS
     hours
    0.17
     hour
    0.17
     Hour
    0.16
     Hours
    0.16
    Hours
    0.14
    hours
    0.13
    -hour
    0.12
    -hours
    0.12
    hour
    0.12
    _hour
    0.12
    Act Density 0.028%

    No Known Activations