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

    Neuronpedia

    INDEX
    Explanations

    information processing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :
    0.51
    ,
    0.47
    ery
    0.47
     जैसे
    0.46
    Re
    0.46
     ду
    0.46
    '
    0.45
    *
    0.45
    ique
    0.44
    /
    0.43
    POSITIVE LOGITS
     linguaggio
    0.54
     cuore
    0.52
     astonished
    0.51
     automakers
    0.50
     disintegrated
    0.50
     bisogno
    0.49
     unseren
    0.49
     ounces
    0.48
    σουν
    0.48
     nome
    0.48
    Act Density 0.001%

    No Known Activations