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

    Neuronpedia

    INDEX
    Explanations

    music videos

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ator
    0.59
    üne
    0.58
    ime
    0.57
    émi
    0.57
     पुनः
    0.55
    émie
    0.55
     धूप
    0.55
    ες
    0.54
    pture
    0.54
    ôme
    0.54
    POSITIVE LOGITS
    v
    0.68
        
    0.59
     acabar
    0.57
     stars
    0.55
     laborales
    0.54
     basis
    0.54
     ITA
    0.54
     hemat
    0.53
     rn
    0.53
     ayud
    0.53
    Act Density 0.001%

    No Known Activations