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

    Neuronpedia

    INDEX
    Explanations

    Being a role model

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ForResult
    -0.07
     Fragen
    -0.07
    系統
    -0.06
    世
    -0.06
     prefers
    -0.06
    wu
    -0.06
    \Config
    -0.06
     optimized
    -0.06
    NETWORK
    -0.06
     воды
    -0.06
    POSITIVE LOGITS
    _spaces
    0.07
    urma
    0.07
    upp
    0.06
     unicode
    0.06
    fung
    0.06
     mül
    0.06
     літ
    0.06
    <u
    0.06
    shortcut
    0.06
    ibur
    0.06
    Act Density 0.288%

    No Known Activations