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

    Neuronpedia

    INDEX
    Explanations

    text fragments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .distance
    -0.08
    /photos
    -0.08
    /topics
    -0.08
    .Distance
    -0.08
    	from
    -0.08
     동시에
    -0.08
    /value
    -0.08
    ifts
    -0.08
     Prediction
    -0.07
     집중
    -0.07
    POSITIVE LOGITS
     ordinary
    0.08
    Sales
    0.08
     Loyola
    0.08
    ರಾದ
    0.08
    komsten
    0.08
    Captain
    0.07
    ,↵
    0.07
     oído
    0.07
     ,↵↵
    0.07
    ado
    0.07
    Act Density 0.126%

    No Known Activations