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

    Neuronpedia

    INDEX
    Explanations

    code/documentation snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sigue
    -0.07
     noodles
    -0.07
     deneyim
    -0.07
     назна
    -0.07
     interle
    -0.07
     Evropy
    -0.06
    .Pow
    -0.06
     overloaded
    -0.06
    .identity
    -0.06
     musique
    -0.06
    POSITIVE LOGITS
    	U
    0.07
     stash
    0.06
    Blank
    0.06
    istan
    0.06
     Stevens
    0.06
    ULA
    0.06
    .handleSubmit
    0.06
    �
    0.06
     떠
    0.06
    STIT
    0.06
    Act Density 0.087%

    No Known Activations