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

    Neuronpedia

    INDEX
    Explanations

    Route

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     composed
    -0.91
     Route
    -0.68
    躇
    -0.67
    composed
    -0.66
     composée
    -0.65
    StructEnd
    -0.65
     normaux
    -0.65
    numerusform
    -0.64
     extérieures
    -0.63
     ApiException
    -0.62
    POSITIVE LOGITS
     the
    0.58
    <bos>
    0.53
     To
    0.48
     Def
    0.47
     
    0.45
    TagMode
    0.44
     a
    0.43
     l
    0.43
    loride
    0.43
     "
    0.42
    Act Density 0.332%

    No Known Activations