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

    Neuronpedia

    INDEX
    Explanations

    the word "description"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ιβ
    0.38
     skol
    0.36
    Monthly
    0.36
     erc
    0.35
    細菌
    0.35
     corretamente
    0.35
     eax
    0.34
    ண்மை
    0.34
     correctamente
    0.34
     antigenic
    0.34
    POSITIVE LOGITS
     description
    0.55
    Description
    0.54
     Description
    0.54
     descripción
    0.53
    Descrição
    0.51
     Descripción
    0.50
    beschreibung
    0.48
    DESCRIPTION
    0.47
     Beschreibung
    0.46
    description
    0.46
    Act Density 0.004%

    No Known Activations