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

    Neuronpedia

    INDEX
    Explanations

    graduation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -counter
    -0.07
     granular
    -0.07
    kaj
    -0.07
    History
    -0.07
    .startswith
    -0.07
     initiated
    -0.07
     Everywhere
    -0.07
     ответ
    -0.07
     LARGE
    -0.07
     internal
    -0.07
    POSITIVE LOGITS
     graduating
    0.16
    毕业
    0.16
     graduation
    0.15
     graduates
    0.13
     attainment
    0.12
     diplôm
    0.12
     Graduation
    0.11
     �
    0.11
     Abschluss
    0.11
     culmination
    0.11
    Act Density 0.056%

    No Known Activations