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

    Neuronpedia

    INDEX
    Explanations

    code and technical articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cous
    -0.07
     simples
    -0.07
    بير
    -0.07
    目的
    -0.06
     cabbage
    -0.06
    prime
    -0.06
    五月
    -0.06
    الس
    -0.06
    �
    -0.06
     privileges
    -0.06
    POSITIVE LOGITS
     dành
    0.06
    -enh
    0.06
    ภาคม
    0.06
     har
    0.06
     noveller
    0.06
    990
    0.06
     unnamed
    0.06
    TRACK
    0.06
     golden
    0.06
    athan
    0.06
    Act Density 0.000%

    No Known Activations