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

    Neuronpedia

    INDEX
    Explanations

    names and terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ujuan
    0.61
    ante
    0.52
    io
    0.51
    inerja
    0.49
    itabbo
    0.49
    ್ಟ
    0.48
    ífer
    0.47
    ujan
    0.47
    supported
    0.46
    iyi
    0.46
    POSITIVE LOGITS
     Esh
    0.46
     undisclosed
    0.46
    Unnamed
    0.46
     folk
    0.45
     Folk
    0.44
     blooming
    0.44
     Croatian
    0.44
     directors
    0.43
     Jacques
    0.42
     impenetrable
    0.42
    Act Density 0.001%

    No Known Activations