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

    Neuronpedia

    INDEX
    Explanations

    seq

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ქ
    -0.08
    纻
    -0.07
    哂
    -0.07
    undra
    -0.07
    俫
    -0.07
     får
    -0.07
    浯
    -0.07
    旺
    -0.07
    ɒ
    -0.07
    栳
    -0.07
    POSITIVE LOGITS
    BLEM
    0.07
     Cara
    0.07
    annah
    0.07
     ropes
    0.07
     Metal
    0.07
    ると
    0.07
     ali
    0.07
    bai
    0.07
    ']:↵
    0.07
    liquid
    0.07
    Act Density 0.004%

    No Known Activations