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

    Neuronpedia

    INDEX
    Explanations

    topics and contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ॉन
    0.47
     eléctrica
    0.44
    šť
    0.43
     মেডিক্যাল
    0.42
    Ľ
    0.42
    ন্দ
    0.41
     सेंसर
    0.40
     Electrode
    0.40
     опа
    0.39
     ब्रिज
    0.39
    POSITIVE LOGITS
     cheered
    0.55
     resurrect
    0.51
    🥰
    0.51
     reintegr
    0.50
     nemat
    0.49
     Yeshu
    0.49
     berths
    0.48
    organization
    0.47
    Gur
    0.47
     cheering
    0.47
    Act Density 0.000%

    No Known Activations