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

    Neuronpedia

    INDEX
    Explanations

    for/all

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     новые
    -0.07
    Json
    -0.07
    чно
    -0.07
     Safe
    -0.06
     Mojo
    -0.06
    -engine
    -0.06
    Variable
    -0.06
     Us
    -0.06
    aceous
    -0.06
    -0.06
    POSITIVE LOGITS
     refute
    0.07
    HOLDER
    0.07
     refl
    0.06
    ：<
    0.06
     shines
    0.06
    ๐
    0.06
     gb
    0.06
     singer
    0.06
     cdr
    0.06
    .iloc
    0.06
    Act Density 0.009%

    No Known Activations