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

    Neuronpedia

    INDEX
    Explanations

    entity followed by action or description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    嚷
    0.45
     شہر
    0.44
    Amt
    0.40
    ità
    0.39
    صیٰ
    0.39
     город
    0.39
    Prosec
    0.38
    ໄຂ
    0.38
    বৃহস্পতিবার
    0.37
     فیصد
    0.37
    POSITIVE LOGITS
     ఇలా
    0.47
    motivation
    0.42
     Beziehungen
    0.42
     lernen
    0.42
     manchmal
    0.41
     monoton
    0.41
     English
    0.40
     zmi
    0.40
     zgod
    0.40
     おすすめ
    0.40
    Act Density 0.005%

    No Known Activations