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

    Neuronpedia

    INDEX
    Explanations

    medical/mechanical contexts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     amp
    -0.54
     an
    -0.51
     tap
    -0.51
     appeal
    -0.50
     tendon
    -0.49
     tend
    -0.49
     tal
    -0.48
     fun
    -0.48
     manifest
    -0.47
     jam
    -0.46
    POSITIVE LOGITS
     houſe
    0.76
     ſtate
    0.75
     poffible
    0.75
     Majefty
    0.73
     Theſe
    0.73
     pleaſure
    0.73
     Reſ
    0.71
     purpoſe
    0.70
     cauſe
    0.67
     Jefus
    0.67
    Act Density 0.219%

    No Known Activations