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

    Neuronpedia

    INDEX
    Explanations

    miscellaneous text excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     지정
    -0.07
    نه
    -0.06
    _wire
    -0.06
     Unit
    -0.06
     senses
    -0.06
     cuis
    -0.06
     alliance
    -0.06
     شهرستان
    -0.06
    _report
    -0.06
    parsed
    -0.06
    POSITIVE LOGITS
     kvinnor
    0.07
     Blick
    0.06
    };↵↵↵↵
    0.06
    ');↵↵↵
    0.06
     objedn
    0.06
    Volt
    0.06
     Plaintiff
    0.06
    optimize
    0.06
     vx
    0.06
    ANCES
    0.06
    Act Density 0.000%

    No Known Activations