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

    Neuronpedia

    INDEX
    Explanations

    .android

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ################
    -0.06
     존
    -0.06
     Output
    -0.06
    ckeditor
    -0.06
    irthday
    -0.06
     covid
    -0.06
    vailability
    -0.06
     
    -0.06
     resign
    -0.06
    ibraltar
    -0.06
    POSITIVE LOGITS
    .android
    0.09
    brates
    0.07
     Bent
    0.07
    	Server
    0.07
     blunt
    0.06
    _HEX
    0.06
     ning
    0.06
    A
    0.06
    بس
    0.06
    왔다
    0.06
    Act Density 0.001%

    No Known Activations