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

    Neuronpedia

    INDEX
    Explanations

    business leader profiles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dialogs
    -0.09
     OPTIONS
    -0.08
    OPTIONS
    -0.08
     ছাত্র
    -0.08
    /dialog
    -0.08
    quette
    -0.07
    veloper
    -0.07
     Venezuela
    -0.07
     Student
    -0.07
    莫
    -0.07
    POSITIVE LOGITS
    атья
    0.11
     Sat
    0.11
     Sund
    0.10
    Sat
    0.09
     feast
    0.09
     отметил
    0.09
    _sat
    0.09
    ihanna
    0.09
    Mary
    0.08
     Res
    0.08
    Act Density 0.003%

    No Known Activations