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

    Neuronpedia

    INDEX
    Explanations

    Safety

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Threads
    -0.07
    Lead
    -0.07
     Stim
    -0.07
     Canucks
    -0.06
     nhiễm
    -0.06
    إنجليزية
    -0.06
    нок
    -0.06
    Conn
    -0.06
     Ingram
    -0.06
    ्रश
    -0.06
    POSITIVE LOGITS
     safety
    0.20
     Safety
    0.19
    Safety
    0.14
    afety
    0.11
    ETY
    0.10
     pes
    0.08
     Justice
    0.08
     Fan
    0.07
    asily
    0.07
    (ff
    0.07
    Act Density 0.017%

    No Known Activations