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

    Neuronpedia

    INDEX
    Explanations

    titles and salutations Mx

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ($_
    0.49
    resize
    0.49
    m
    0.47
    oping
    0.46
    portions
    0.45
    widet
    0.44
    bit
    0.44
    diamond
    0.44
     domingo
    0.44
     διά
    0.44
    POSITIVE LOGITS
     Moreau
    0.44
     Group
    0.43
     Pfeiffer
    0.42
     Born
    0.42
    aeus
    0.41
    晗
    0.41
     Aviv
    0.40
     Frisch
    0.40
     evokes
    0.40
     Choosing
    0.40
    Act Density 0.003%

    No Known Activations