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

    Neuronpedia

    INDEX
    Explanations

    to announce

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    appré
    0.44
    мую
    0.42
    理解
    0.41
     accessing
    0.40
     interpreting
    0.40
    avoid
    0.40
     específicos
    0.40
     faktisk
    0.40
     మాత్రం
    0.39
    想
    0.39
    POSITIVE LOGITS
     announce
    0.66
     anunciar
    0.56
     announces
    0.55
     Announces
    0.52
     Announced
    0.49
     anunció
    0.49
     annonce
    0.49
     commence
    0.48
     commences
    0.47
    announce
    0.47
    Act Density 0.003%

    No Known Activations