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

    Neuronpedia

    INDEX
    Explanations

    displacement reactions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    imento
    -0.09
     modo
    -0.08
     tasteful
    -0.08
    schule
    -0.08
    Neill
    -0.07
    BOOLEAN
    -0.07
     bigint
    -0.07
    BOOT
    -0.07
    비스
    -0.07
    ভ
    -0.07
    POSITIVE LOGITS
    	swap
    0.08
     चोरी
    0.08
     superiores
    0.08
     holes
    0.08
     Quality
    0.08
    เด็ด
    0.08
     stolen
    0.08
    授权
    0.07
     swap
    0.07
     stopp
    0.07
    Act Density 0.005%

    No Known Activations