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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
     엔
    -0.06
    вод
    -0.06
    :)];↵
    -0.06
     students
    -0.06
     validations
    -0.06
     只
    -0.06
    _latitude
    -0.06
     vocalist
    -0.06
    Scientists
    -0.06
    POSITIVE LOGITS
     договор
    0.07
    .onDestroy
    0.07
    icro
    0.07
     Eag
    0.07
     پیوند
    0.06
    opro
    0.06
    ária
    0.06
    coverage
    0.06
     unreal
    0.06
    strategy
    0.06
    Act Density 0.031%

    No Known Activations