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

    Neuronpedia

    INDEX
    Explanations

    Sensor and technical concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    topics
    0.42
    ጆ
    0.41
    ット
    0.39
     Гульнявыя
    0.38
    ণিজ্য
    0.38
    ത്തില
    0.37
    መሳሳይ
    0.37
     tóp
    0.37
     Стаўкі
    0.37
    釗
    0.37
    POSITIVE LOGITS
    vious
    0.38
    ιδ
    0.38
     backwards
    0.37
     SPL
    0.37
    ńcz
    0.37
    SPL
    0.36
     aware
    0.35
     emuls
    0.35
     transcription
    0.35
    undang
    0.35
    Act Density 0.000%

    No Known Activations