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

    Neuronpedia

    INDEX
    Explanations

    so

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    apiro
    -0.08
    PRIMARY
    -0.07
    líb
    -0.06
     EX
    -0.06
    LLLL
    -0.06
    ddd
    -0.06
    ADR
    -0.06
     REPL
    -0.06
     puedo
    -0.06
     contribute
    -0.06
    POSITIVE LOGITS
     houses
    0.07
    sc
    0.07
    ارات
    0.07
    _slow
    0.07
     万元
    0.07
     facilities
    0.06
    шев
    0.06
     blossom
    0.06
    MainActivity
    0.06
    ("!
    0.06
    Act Density 0.008%

    No Known Activations