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

    Neuronpedia

    INDEX
    Explanations

    bliss

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	Size
    -0.07
     kijken
    -0.07
     estate
    -0.07
     العملية
    -0.07
    (manager
    -0.06
     взя
    -0.06
     size
    -0.06
     operation
    -0.06
     specimens
    -0.06
     Huang
    -0.06
    POSITIVE LOGITS
     commence
    0.07
    ีต
    0.07
     безопас
    0.07
    _Account
    0.07
    illusion
    0.07
     Griff
    0.06
    FFT
    0.06
    истра
    0.06
     개발
    0.06
     Urg
    0.06
    Act Density 0.002%

    No Known Activations