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

    Neuronpedia

    INDEX
    Explanations

    submit or return instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     roller
    -0.07
    "]=
    -0.06
    Disclosure
    -0.06
    br
    -0.06
    translator
    -0.06
     sacrifices
    -0.06
    Challenge
    -0.06
    .sw
    -0.06
    ته
    -0.06
     Holl
    -0.06
    POSITIVE LOGITS
    Create
    0.07
    алов
    0.07
    VERTISE
    0.07
    163
    0.06
    656
    0.06
    489
    0.06
    ABI
    0.06
    жі
    0.06
    utex
    0.06
    ивает
    0.06
    Act Density 0.015%

    No Known Activations