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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     panorama
    -0.07
    bor
    -0.07
     sports
    -0.06
    ("./
    -0.06
    omes
    -0.06
    -0.06
     Abbas
    -0.06
     storm
    -0.06
     Penny
    -0.06
    бор
    -0.06
    POSITIVE LOGITS
    Це
    0.07
     backstage
    0.06
     afflicted
    0.06
    .Member
    0.06
    ी,
    0.06
    UD
    0.06
     Bab
    0.06
     kj
    0.06
     εκεί
    0.06
    	else
    0.06
    Act Density 0.035%

    No Known Activations