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

    Neuronpedia

    INDEX
    Explanations

    Crisis Lifeline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    adas
    0.63
     and
    0.62
     &
    0.61
     consisting
    0.60
    ↵
    0.58
     that
    0.58
     legislation
    0.57
     enabling
    0.57
     provides
    0.56
    ées
    0.55
    POSITIVE LOGITS
     wundersch
    0.69
     اهلا
    0.66
     sowie
    0.66
    umlahan
    0.65
     важней
    0.64
    PROTON
    0.64
    ذاب
    0.64
     QUILL
    0.64
     Mahall
    0.64
    ontiti
    0.64
    Act Density 0.063%

    No Known Activations