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

    Neuronpedia

    INDEX
    Explanations

    AI model-related comments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    exus
    -0.06
     chỉ
    -0.06
    OG
    -0.06
     سفر
    -0.06
    ikon
    -0.06
    ाइव
    -0.06
     цен
    -0.06
    _basename
    -0.06
    κού
    -0.06
    mu
    -0.06
    POSITIVE LOGITS
     planting
    0.07
     banks
    0.06
    (existing
    0.06
     Armed
    0.06
     "",↵
    0.06
     evolution
    0.06
     Extras
    0.06
     grö
    0.06
    .Split
    0.06
    happy
    0.06
    Act Density 0.023%

    No Known Activations