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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    phe
    -0.06
     corpses
    -0.06
    ULSE
    -0.06
     forwards
    -0.06
    hest
    -0.06
    stroy
    -0.05
     كسارة
    -0.05
    جع
    -0.05
    Advertisement
    -0.05
    rosso
    -0.05
    POSITIVE LOGITS
     by
    0.08
    研究
    0.07
    (xhr
    0.07
    ....↵↵
    0.07
    ecause
    0.07
    ?\
    0.07
    	onClick
    0.07
    िकत
    0.07
    .running
    0.07
     getTotal
    0.07
    Act Density 0.057%

    No Known Activations