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

    Neuronpedia

    INDEX
    Explanations

    argumentative language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mounts
    -0.07
    Diff
    -0.07
     SPECIAL
    -0.07
    ilion
    -0.06
    	buffer
    -0.06
    igmoid
    -0.06
    ifdef
    -0.06
    ②
    -0.06
    eworld
    -0.06
    CCCC
    -0.06
    POSITIVE LOGITS
     dislikes
    0.06
     cumshot
    0.06
     sendMessage
    0.06
     sống
    0.06
    掌
    0.06
    uario
    0.06
    ุงเทพมหานคร
    0.06
     chuẩn
    0.06
     реч
    0.06
     года
    0.06
    Act Density 0.116%

    No Known Activations