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

    Neuronpedia

    INDEX
    Explanations

    explaining literal meanings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pository
    0.75
     clinicians
    0.72
    pyrazol
    0.71
    ौल
    0.71
     glEnable
    0.70
    enario
    0.70
    JSONException
    0.69
     UIImage
    0.68
     oxides
    0.67
    Dmat
    0.67
    POSITIVE LOGITS
    literally
    1.88
     literally
    1.74
     literalmente
    1.72
     Literally
    1.69
     буквально
    1.26
     literal
    1.25
     meaning
    1.20
    pronounced
    1.17
    literal
    1.17
    meaning
    1.16
    Act Density 0.579%

    No Known Activations