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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    692
    -0.07
     brought
    -0.06
    布
    -0.06
     đứng
    -0.06
     Turning
    -0.06
     Jama
    -0.06
    .loss
    -0.06
    Born
    -0.06
     bắt
    -0.06
    	stop
    -0.06
    POSITIVE LOGITS
    970
    0.07
    -packages
    0.07
    34
    0.07
     ecstasy
    0.07
    )&&
    0.07
    geo
    0.07
    іду
    0.06
    apons
    0.06
    .activ
    0.06
    ehler
    0.06
    Act Density 0.219%

    No Known Activations