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

    Neuronpedia

    INDEX
    Explanations

    present progressive verbs

    oai_token-act-pair · gemini-2.0-flash

    being

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     also
    -0.98
     still
    -0.96
    still
    -0.89
     already
    -0.83
     fortfarande
    -0.82
    already
    -0.77
    also
    -0.75
     ancora
    -0.74
     always
    -0.73
     usually
    -0.73
    POSITIVE LOGITS
    RegressionTest
    0.61
     المعيارى
    0.59
    DockStyle
    0.58
     виправивши
    0.58
    ]--;
    0.57
    ValueStyle
    0.56
     hunted
    0.56
    abetes
    0.56
    évaluateur
    0.52
    EDEFAULT
    0.52
    Act Density 2.015%

    No Known Activations