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

    Neuronpedia

    INDEX
    Explanations

    code snippets and syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     字
    -0.07
    ，从
    -0.07
     nuclear
    -0.07
     hafta
    -0.06
    .Parameters
    -0.06
    )-(
    -0.06
     Ko
    -0.06
     напис
    -0.06
     Б
    -0.06
     испыт
    -0.06
    POSITIVE LOGITS
    iterr
    0.06
     comply
    0.06
     vagina
    0.06
    ystack
    0.06
    abh
    0.06
    *r
    0.06
     воду
    0.06
    �
    0.06
     BLL
    0.06
     몇
    0.06
    Act Density 0.000%

    No Known Activations