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

    Neuronpedia

    INDEX
    Explanations

    first edition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Klicken
    0.45
    '
    0.42
     clickable
    0.40
     Animal
    0.40
     Theta
    0.39
     theta
    0.39
     clips
    0.39
    Clip
    0.38
     Snow
    0.38
     clip
    0.37
    POSITIVE LOGITS
    edition
    0.86
     edition
    0.83
     editions
    0.82
     edizione
    0.80
     edición
    0.76
    edizione
    0.75
     ediciones
    0.73
     издания
    0.71
     édition
    0.69
     edição
    0.68
    Act Density 0.001%

    No Known Activations