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

    Neuronpedia

    INDEX
    Explanations

    (*

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ω
    -0.07
     وش
    -0.07
    \Test
    -0.07
    .zh
    -0.06
    chosen
    -0.06
    nitř
    -0.06
    ologue
    -0.06
     cerco
    -0.06
    			↵
    -0.05
     descriptor
    -0.05
    POSITIVE LOGITS
    inoa
    0.07
    ени
    0.07
    евид
    0.07
    oen
    0.07
    Ann
    0.07
    -approved
    0.07
    olie
    0.07
    ATION
    0.06
    eline
    0.06
     Hong
    0.06
    Act Density 0.000%

    No Known Activations