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

    Neuronpedia

    INDEX
    Explanations

    lexical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Metadata
    -0.09
     Madness
    -0.09
     Metadata
    -0.09
     yeah
    -0.08
     anything
    -0.08
    _metadata
    -0.08
    まあ
    -0.08
    icio
    -0.08
    Opts
    -0.08
     Cmd
    -0.08
    POSITIVE LOGITS
     exaggerated
    0.09
     partes
    0.08
     con
    0.08
     употреб
    0.08
     gest
    0.08
     partnerships
    0.08
     exagger
    0.07
     verður
    0.07
     bil
    0.07
    .keyword
    0.07
    Act Density 0.005%

    No Known Activations