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

    Neuronpedia

    INDEX
    Explanations

    programming/documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _UPDATE
    -0.07
     Zhang
    -0.07
     refriger
    -0.07
     ري
    -0.07
     add
    -0.07
     Mann
    -0.06
     있던
    -0.06
     сор
    -0.06
    <Props
    -0.06
     drv
    -0.06
    POSITIVE LOGITS
    undra
    0.06
     outward
    0.06
    instrument
    0.06
     Herald
    0.06
    abase
    0.06
    omination
    0.06
     cardinal
    0.06
     طل
    0.06
     expérience
    0.06
    ़ो
    0.06
    Act Density 0.000%

    No Known Activations