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

    Neuronpedia

    INDEX
    Explanations

    bullet points and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    டியான
    0.42
    ären
    0.39
     Ancient
    0.39
    স্বামী
    0.38
    isateur
    0.37
    volved
    0.37
    ゥ
    0.37
     உண்மையில்
    0.37
    缓
    0.37
    ાવ
    0.37
    POSITIVE LOGITS
     subiect
    0.47
     sujets
    0.46
    EU
    0.46
     topic
    0.44
    xml
    0.44
    topics
    0.41
    Lifecycle
    0.41
     subject
    0.41
    life
    0.41
    topic
    0.41
    Act Density 0.000%

    No Known Activations