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

    Neuronpedia

    INDEX
    Explanations

    explaining occurrences after specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     can
    0.55
     are
    0.54
     to
    0.51
     is
    0.51
    Salah
    0.48
    Vr
    0.48
    War
    0.48
    Waters
    0.47
                   
    0.47
     Obr
    0.46
    POSITIVE LOGITS
    ة
    0.71
     LISA
    0.57
    ีย
    0.54
    ürdig
    0.53
    ك
    0.52
    టో
    0.52
    ం
    0.52
    ے
    0.51
    ing
    0.50
    .
    0.50
    Act Density 0.000%

    No Known Activations