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

    Neuronpedia

    INDEX
    Explanations

    we need

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ою
    0.50
    zeitig
    0.50
    ologio
    0.45
    zeit
    0.45
     Lama
    0.44
    nums
    0.44
    esthetic
    0.44
     পেতে
    0.43
     confounding
    0.43
     asian
    0.43
    POSITIVE LOGITS
    Panning
    0.55
    \}-
    0.53
        
    0.53
    ទឹក
    0.52
    APPLE
    0.49
    N
    0.49
    ;-
    0.48
    Caro
    0.48
    PVC
    0.47
    Portrait
    0.47
    Act Density 0.001%

    No Known Activations