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

    Neuronpedia

    INDEX
    Explanations

    references to stars and notable figures in music or entertainment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    music stars and bands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Vikipedi
    -0.46
    extAlignment
    -0.41
    Prevention
    -0.37
    (=)
    -0.37
     Gate
    -0.36
    thenReturn
    -0.36
     دب
    -0.36
    Gruß
    -0.35
    NSIndexPath
    -0.35
     cucchiaio
    -0.35
    POSITIVE LOGITS
     Rockstar
    1.18
     Superstar
    0.56
     superstars
    0.54
    bands
    0.51
    Bands
    0.50
    achella
    0.50
    estars
    0.49
     bands
    0.49
     becauſe
    0.48
    şört
    0.48
    Act Density 0.007%

    No Known Activations