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

    Neuronpedia

    INDEX
    Explanations

    evaluates mathematical expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Villa
    -0.07
    cascade
    -0.07
    ussy
    -0.07
    宫
    -0.06
     mosaic
    -0.06
     Monsanto
    -0.06
    ulously
    -0.06
    apolis
    -0.06
    WG
    -0.06
    每年
    -0.06
    POSITIVE LOGITS
     먼
    0.08
     odpowied
    0.08
    (expression
    0.07
     amacıyla
    0.07
    챈
    0.07
     WAN
    0.07
    -CN
    0.06
     ℕ
    0.06
    _infos
    0.06
     tops
    0.06
    Act Density 0.051%

    No Known Activations