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

    Neuronpedia

    INDEX
    Explanations

    XML code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    instead
    -0.07
     travel
    -0.07
     getline
    -0.06
    Leading
    -0.06
     tokenize
    -0.06
    -----------↵↵
    -0.06
     examine
    -0.06
     thorough
    -0.06
     missing
    -0.06
     Tonight
    -0.06
    POSITIVE LOGITS
    antas
    0.07
     lament
    0.07
    antd
    0.07
    .hstack
    0.07
    ноп
    0.07
    _proba
    0.06
    resenter
    0.06
    zeug
    0.06
    юр
    0.06
    _Get
    0.06
    Act Density 0.016%

    No Known Activations