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

    Neuronpedia

    INDEX
    Explanations

    adjusting/controlling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    еч
    -0.07
    $sub
    -0.07
    ριά
    -0.07
    亦
    -0.07
     저
    -0.07
     ashamed
    -0.07
     εξ
    -0.07
    儿
    -0.06
    แท
    -0.06
     Централь
    -0.06
    POSITIVE LOGITS
    Food
    0.07
    achinery
    0.06
    /T
    0.06
    rada
    0.06
    (simp
    0.06
    	constexpr
    0.06
    62
    0.06
    Ne
    0.06
    [int
    0.06
     collision
    0.06
    Act Density 0.007%

    No Known Activations