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

    Neuronpedia

    INDEX
    Explanations

    Question/Answer pairs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .sponge
    -0.07
     영향을
    -0.07
     paraph
    -0.07
    ськими
    -0.06
    _workers
    -0.06
    
    -0.06
    	sprite
    -0.06
    Teams
    -0.06
    mav
    -0.06
    gems
    -0.06
    POSITIVE LOGITS
     ignore
    0.07
    izzy
    0.07
    ỉnh
    0.06
     gratuites
    0.06
    уд
    0.06
     escalated
    0.06
     على
    0.06
    .precision
    0.06
     لكل
    0.06
     Listed
    0.05
    Act Density 0.130%

    No Known Activations