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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to scientific studies or to legal and financial problems

    oai_token-act-pair · gemini-2.0-flash

    Tax problems

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MessageOf
    -0.67
     дописавши
    -0.63
     jLabel
    -0.63
     ویکی‌پدیای
    -0.63
    NOPQRST
    -0.61
    theless
    -0.60
    ETHING
    -0.60
     CURIAM
    -0.59
     <=",
    -0.59
     insuffisamment
    -0.58
    POSITIVE LOGITS
     Are
    0.95
     Make
    0.84
    Are
    0.82
     Leave
    0.79
     Reach
    0.78
     Achieve
    0.77
     Aren
    0.77
     Tell
    0.77
    Do
    0.75
     Do
    0.75
    Act Density 13.741%

    No Known Activations