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

    Neuronpedia

    INDEX
    Explanations

    joy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     joy
    -1.30
    joy
    -1.30
     Joy
    -1.27
    Joy
    -1.22
     JOY
    -0.98
    JOY
    -0.98
     compound
    -0.87
    joys
    -0.86
     joys
    -0.79
     findings
    -0.78
    POSITIVE LOGITS
    e
    0.73
    ed
    0.64
    ########.
    0.61
    ear
    0.60
    tagHelperRunner
    0.56
    VIAF
    0.54
    eater
    0.53
    ef
    0.53
     iprot
    0.53
    equi
    0.52
    Act Density 2.421%

    No Known Activations