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

    Neuronpedia

    INDEX
    Explanations

    structured lists and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    akse
    0.46
    కుంటు
    0.43
    咶
    0.42
    avises
    0.41
     jornalista
    0.41
     ආරක්ෂ
    0.40
    avacanam
    0.40
    rophication
    0.39
    lyPlugin
    0.39
    मतौर
    0.39
    POSITIVE LOGITS
    And
    0.47
     which
    0.45
     مض
    0.44
    2
    0.43
     Και
    0.43
     [
    0.42
     potentially
    0.40
    HG
    0.39
    HP
    0.39
     potential
    0.39
    Act Density 0.002%

    No Known Activations