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

    Neuronpedia

    INDEX
    Explanations

    ol

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -scenes
    -0.07
     Quran
    -0.06
    .decrypt
    -0.06
    oidal
    -0.06
    ampo
    -0.06
    .none
    -0.06
     contradictory
    -0.06
     Bride
    -0.06
     Babe
    -0.06
     shouting
    -0.06
    POSITIVE LOGITS
    農
    0.07
     seamlessly
    0.07
    군
    0.07
    onds
    0.07
    _dns
    0.06
    Similarly
    0.06
     slept
    0.06
    .Device
    0.06
     hem
    0.06
     treating
    0.06
    Act Density 0.000%

    No Known Activations