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

    Neuronpedia

    INDEX
    Explanations

    (-

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     csak
    -0.07
    /C
    -0.06
     kind
    -0.06
    Door
    -0.06
     тепер
    -0.06
     spelling
    -0.06
    ürnberg
    -0.06
     모습
    -0.06
    _students
    -0.06
     During
    -0.06
    POSITIVE LOGITS
    orners
    0.07
    Beth
    0.07
    }');↵
    0.06
     earn
    0.06
    Ensure
    0.06
     влаж
    0.06
    __((
    0.06
    eners
    0.06
    One
    0.06
    _price
    0.06
    Act Density 0.000%

    No Known Activations