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

    Neuronpedia

    INDEX
    Explanations

    ™

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ich
    -0.77
    -
    -0.66
    tm
    -0.59
     Mars
    -0.57
    ™
    -0.57
     Man
    -0.56
    TM
    -0.52
    "-
    -0.52
    i
    -0.51
    wald
    -0.51
    POSITIVE LOGITS
     Anſ
    0.97
     myſelf
    0.94
     itſelf
    0.93
     pleaſure
    0.91
     purpoſe
    0.90
     ſte
    0.89
     ſta
    0.89
     greateſt
    0.89
     Efq
    0.89
     ſtate
    0.88
    Act Density 0.349%

    No Known Activations