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

    Neuronpedia

    INDEX
    Explanations

    legal disputes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dictates
    -0.06
     Nan
    -0.06
    اقع
    -0.06
     uncomment
    -0.06
    Therefore
    -0.06
     existe
    -0.06
    -imm
    -0.06
    iyorum
    -0.06
     parental
    -0.06
     ritual
    -0.06
    POSITIVE LOGITS
    ілля
    0.08
    .toolStripButton
    0.07
    384
    0.07
    PAGE
    0.06
    něm
    0.06
     valves
    0.06
    बल
    0.06
     {}.
    0.06
     文章
    0.06
    (false
    0.06
    Act Density 0.020%

    No Known Activations