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

    Neuronpedia

    INDEX
    Explanations

    the word "lift" and related concepts

    oai_token-act-pair · gemini-2.0-flash

    lift

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     démocr
    -0.95
     fermés
    -0.93
     sanitaires
    -0.92
     espirituales
    -0.88
     rempliss
    -0.87
    ագրություններ
    -0.86
     financières
    -0.85
     avoient
    -0.85
     anún
    -0.85
    IsMutable
    -0.85
    POSITIVE LOGITS
    <bos>
    0.58
     parah
    0.53
     Bourgoin
    0.52
     retra
    0.51
     finally
    0.49
     parti
    0.47
     cóc
    0.46
    ThemeOverlay
    0.46
     ra
    0.46
     admitted
    0.46
    Act Density 1.593%

    No Known Activations