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

    Neuronpedia

    INDEX
    Explanations

    descriptions of places and things to do in cities

    oai_token-act-pair · gemini-2.0-flash

    restaurants and travel

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    adaptiveStyles
    -0.69
    #+#
    -0.60
     ***!
    -0.60
    +#+#
    -0.57
     spéc
    -0.57
     <<<<<<<<<<<<<<
    -0.54
    يكب
    -0.53
    ectoria
    -0.52
    /*
    -0.51
     Chaudh
    -0.49
    POSITIVE LOGITS
    Geplaatst
    0.71
     Roskov
    0.57
    fastjson
    0.54
     smtplib
    0.54
     thyself
    0.53
     Vira
    0.53
     ComVisible
    0.50
     resultMap
    0.49
     gneiss
    0.49
    URLException
    0.49
    Act Density 1.736%

    No Known Activations