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

    Neuronpedia

    INDEX
    Explanations

    FM

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Shen
    -0.06
    	scanf
    -0.06
     baseline
    -0.06
    áš
    -0.06
    ']],↵
    -0.06
     sorry
    -0.06
    delete
    -0.06
     uomini
    -0.05
    Csv
    -0.05
    baseline
    -0.05
    POSITIVE LOGITS
    _detector
    0.08
     FM
    0.08
     Television
    0.07
    .fm
    0.07
     تصمیم
    0.07
     مما
    0.06
    	Vk
    0.06
    �
    0.06
    375
    0.06
    DEM
    0.06
    Act Density 0.002%

    No Known Activations