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

    Neuronpedia

    INDEX
    Explanations

    Verbs in sentences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.91
    hould
    -0.91
    should
    -0.91
     متعلقه
    -0.89
    SequentialGroup
    -0.83
    rrggbb
    -0.83
     should
    -0.81
     CURIAM
    -0.78
    tagHelperRunner
    -0.78
     arşivlendi
    -0.77
    POSITIVE LOGITS
     the
    0.81
     some
    0.68
     
    0.68
     '
    0.67
     it
    0.66
     a
    0.62
     "
    0.62
     “
    0.56
     ‘
    0.56
     off
    0.55
    Act Density 0.051%

    No Known Activations