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

    Neuronpedia

    INDEX
    Explanations

    crest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    盦
    -0.08
    ｠
    -0.07
    烺
    -0.07
    杓
    -0.06
     illumin
    -0.06
     RAND
    -0.06
    ஜ
    -0.06
     strang
    -0.06
     gle
    -0.06
     clim
    -0.06
    POSITIVE LOGITS
    滚球
    0.07
    她说
    0.07
     SRC
    0.07
    ออนไล
    0.07
    Montserrat
    0.07
    tória
    0.07
     Su
    0.07
     Kitty
    0.06
    Oct
    0.06
    Laugh
    0.06
    Act Density 0.002%

    No Known Activations