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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.69
     that
    -0.65
     you
    -0.63
     I
    -0.56
     then
    -0.55
     aktiviteter
    -0.54
     väli
    -0.53
     just
    -0.52
    .
    -0.51
     régl
    -0.50
    POSITIVE LOGITS
    tvguidetime
    0.88
    GEBURTSDATUM
    0.81
     ProtoMessage
    0.80
     }}$}
    0.77
     CreateTagHelper
    0.71
     MainAxisSize
    0.69
     utafitiHapana
    0.67
    +#+#
    0.66
     snippetHide
    0.66
    GEBURTS
    0.65
    Act Density 0.032%

    No Known Activations