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

    Neuronpedia

    INDEX
    Explanations

    dash library

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     secondo
    -0.07
     tile
    -0.06
     estado
    -0.06
     cowboy
    -0.06
     ruled
    -0.06
     efficiency
    -0.06
     kp
    -0.06
    =sub
    -0.06
     pretext
    -0.06
    grow
    -0.06
    POSITIVE LOGITS
     MCP
    0.07
    fieldName
    0.07
     Heading
    0.06
    hoc
    0.06
    licated
    0.06
     MONTH
    0.06
     وضع
    0.06
     milestones
    0.06
     Brother
    0.06
     Brain
    0.06
    Act Density 0.002%

    No Known Activations