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

    Neuronpedia

    INDEX
    Explanations

    technical/research language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .with
    -0.07
    /renderer
    -0.07
    Completion
    -0.07
     modelo
    -0.06
    _button
    -0.06
    ACING
    -0.06
     rack
    -0.06
     investigación
    -0.06
     darkest
    -0.06
    cool
    -0.06
    POSITIVE LOGITS
     Pey
    0.06
    wine
    0.06
    --------------↵
    0.06
    VERTEX
    0.06
    QueryString
    0.06
     responder
    0.06
    JKLMNOP
    0.06
    _known
    0.06
     Deserialize
    0.06
     #-}↵↵
    0.06
    Act Density 0.458%

    No Known Activations