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

    Neuronpedia

    INDEX
    Explanations

    a name, a discovery, a choice, a difference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Details
    0.39
     চিঠ
    0.39
     परिणामों
    0.39
     சிந்த
    0.38
     हे
    0.38
    DETAILS
    0.37
     yapılan
    0.37
     pembuatan
    0.37
     DETAILS
    0.37
    ein
    0.36
    POSITIVE LOGITS
     inroads
    0.82
     headway
    0.70
     strides
    0.64
     amends
    0.62
     distinctions
    0.61
     noise
    0.60
     noises
    0.59
     adjustments
    0.59
     difference
    0.59
     assumptions
    0.58
    Act Density 0.023%

    No Known Activations