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

    Neuronpedia

    INDEX
    Explanations

    Jokes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mädchen
    -0.07
     confirmation
    -0.06
     wondering
    -0.06
     slaughter
    -0.06
     bacon
    -0.06
     Lifetime
    -0.06
     builders
    -0.06
     Fantasy
    -0.06
    ponses
    -0.06
     Sheets
    -0.06
    POSITIVE LOGITS
    _bins
    0.07
    EFF
    0.07
    /cmd
    0.07
     tslint
    0.07
     마지막
    0.07
    .BAD
    0.06
     забезпеч
    0.06
     electrom
    0.06
    -Semit
    0.06
    (Gtk
    0.06
    Act Density 0.007%

    No Known Activations