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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     von
    -0.07
    ÇÃO
    -0.07
    ꜥ
    -0.07
    /ion
    -0.07
     Pa
    -0.07
     glitches
    -0.06
    	push
    -0.06
     mit
    -0.06
    .createParallelGroup
    -0.06
     LastName
    -0.06
    POSITIVE LOGITS
    钒
    0.08
    ethod
    0.08
     ?????
    0.07
    buff
    0.07
    帥
    0.07
     Nack
    0.07
    훑
    0.07
    很高
    0.07
    节能减排
    0.07
    美貌
    0.07
    Act Density 0.053%

    No Known Activations