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

    Neuronpedia

    INDEX
    Explanations

    work and jobs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     purpoſe
    -0.96
     Majefty
    -0.91
     raiſ
    -0.90
     quæ
    -0.88
     ſche
    -0.86
     Efq
    -0.85
     potest
    -0.84
     Monfieur
    -0.84
     Reſ
    -0.83
     iſt
    -0.82
    POSITIVE LOGITS
     med
    0.45
    ligh
    0.41
     Se
    0.40
     Care
    0.39
     Stedman
    0.39
    md
    0.39
    flag
    0.38
     or
    0.37
    hif
    0.37
     La
    0.36
    Act Density 0.065%

    No Known Activations