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

    Neuronpedia

    INDEX
    Explanations

    oxidative

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kg
    -0.07
    472
    -0.06
     celebrated
    -0.06
    _dep
    -0.06
    -man
    -0.06
     aaa
    -0.06
     chica
    -0.06
    -0.06
    _attention
    -0.06
     DL
    -0.06
    POSITIVE LOGITS
     oxidative
    0.15
     sexually
    0.07
     sanitary
    0.07
     gruesome
    0.07
     nướng
    0.06
     emotional
    0.06
     Molecular
    0.06
     शर
    0.06
    vic
    0.06
    conomic
    0.06
    Act Density 0.002%

    No Known Activations