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

    Neuronpedia

    INDEX
    Explanations

    Parallel

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     buying
    -0.07
     Marine
    -0.07
     Researchers
    -0.07
     ông
    -0.06
     meme
    -0.06
    Ms
    -0.06
    持
    -0.06
    协助
    -0.06
     charming
    -0.06
    洱
    -0.06
    POSITIVE LOGITS
    仪表
    0.08
    ත
    0.07
    .PackageManager
    0.07
     상태
    0.07
    BACK
    0.07
    ">&
    0.07
    пат
    0.07
    .backup
    0.07
    anova
    0.07
    -input
    0.07
    Act Density 0.002%

    No Known Activations