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

    Neuronpedia

    INDEX
    Explanations

    use lists or paragraphs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    etaan
    0.49
    utam
    0.44
     erfüllt
    0.43
     території
    0.39
     Mormon
    0.39
    kval
    0.39
     Joaquin
    0.38
     Volga
    0.38
    rodní
    0.38
    ð
    0.37
    POSITIVE LOGITS
     groupe
    0.52
     professe
    0.48
     condivid
    0.47
     adicional
    0.45
     contest
    0.45
     comunidad
    0.45
     lancio
    0.45
    टीम
    0.45
     creativa
    0.44
    COME
    0.44
    Act Density 0.001%

    No Known Activations