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

    Neuronpedia

    INDEX
    Explanations

    defining concepts or topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    0.44
     We
    0.44
     we
    0.44
     więc
    0.43
     dessa
    0.42
     podemos
    0.40
     vardır
    0.40
     =
    0.39
     puedes
    0.39
     you
    0.39
    POSITIVE LOGITS
     amid
    0.59
    .«
    0.58
    .”
    0.50
    .''
    0.49
    ."
    0.49
    .`
    0.48
     despite
    0.46
    .“
    0.46
    ".
    0.44
    .’
    0.43
    Act Density 0.064%

    No Known Activations