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

    Neuronpedia

    INDEX
    Explanations

    t

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     انر
    -0.07
    	br
    -0.07
    ovací
    -0.06
    268
    -0.06
    ">

↵
    -0.06
     구성
    -0.06
     біль
    -0.06
    Forge
    -0.06
    ]\
    -0.06
    'Neill
    -0.06
    POSITIVE LOGITS
    LECT
    0.08
    .getZ
    0.07
     subtly
    0.07
    .home
    0.06
     togg
    0.06
    “
    0.06
     anonymously
    0.06
    yük
    0.06
     WHY
    0.06
     loud
    0.06
    Act Density 0.001%

    No Known Activations