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

    Neuronpedia

    INDEX
    Explanations

    ype

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    怀抱
    -0.07
    度过
    -0.07
     Baron
    -0.07
     deducted
    -0.07
    ILLS
    -0.06
     السنة
    -0.06
    до
    -0.06
    eted
    -0.06
     Bod
    -0.06
    ruptions
    -0.06
    POSITIVE LOGITS
     Рус
    0.08
    -ap
    0.08
     templ
    0.07
    aka
    0.07
    	console
    0.07
     türl
    0.07
     Mt
    0.07
    .type
    0.07
    capital
    0.06
    (unique
    0.06
    Act Density 0.002%

    No Known Activations