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

    Neuronpedia

    INDEX
    Explanations

    question marks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Provide
    -0.14
     Myself
    -0.14
     Implementation
    -0.13
     illusions
    -0.12
     musicals
    -0.12
     vantage
    -0.12
     Suppose
    -0.12
    makes
    -0.12
     please
    -0.12
     overshadow
    -0.11
    POSITIVE LOGITS
    0.13
     драм
    0.10
    ...↵↵
    0.10
    […]
    0.10
    ...
    0.10
     нәр
    0.09
    ։↵↵
    0.09
     literal
    0.09
    0.09
    …↵↵
    0.09
    Act Density 0.722%
    No Known Activations