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

    Neuronpedia

    INDEX
    Explanations

    method or function definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .].
    0.68
     Sony
    0.67
     we
    0.64
    :].
    0.63
     ].
    0.61
     ASCII
    0.61
     あなた
    0.61
     Kagan
    0.61
     PNG
    0.61
    ].
    0.59
    POSITIVE LOGITS
     їх
    0.73
     dissociate
    0.70
     jejich
    0.70
     ihres
    0.67
     niiden
    0.66
     их
    0.65
     તેમની
    0.65
    constructor
    0.65
     ihre
    0.63
     kanilang
    0.63
    Act Density 0.115%

    No Known Activations