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

    Neuronpedia

    INDEX
    Explanations

    dangerous

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vibe
    -0.07
    Why
    -0.07
     song
    -0.07
    Snackbar
    -0.07
     radiation
    -0.07
     $(
    -0.07
    Pal
    -0.06
    ({↵↵
    -0.06
    bras
    -0.06
     bog
    -0.06
    POSITIVE LOGITS
    ومات
    0.07
    seniz
    0.06
    储
    0.06
    _export
    0.06
     حم
    0.06
    /frontend
    0.06
     đị
    0.06
    орош
    0.06
     مبانی
    0.06
    -pocket
    0.06
    Act Density 0.041%

    No Known Activations