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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _LIST
    -0.07
    주
    -0.06
    .joda
    -0.06
     palabras
    -0.06
     동안
    -0.06
     emitted
    -0.06
    práv
    -0.06
    anguard
    -0.06
    _FIRE
    -0.06
    _MM
    -0.05
    POSITIVE LOGITS
     reloc
    0.07
    тал
    0.06
    .employee
    0.06
    овал
    0.06
     Thổ
    0.06
    esper
    0.06
     THEY
    0.06
    $select
    0.06
    scaled
    0.06
     frustr
    0.06
    Act Density 0.031%

    No Known Activations