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

    Neuronpedia

    INDEX
    Explanations

    behavioral tendency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    the
    0.43
    launch
    0.41
    t
    0.40
    minus
    0.40
    reibt
    0.40
    vendors
    0.39
    dds
    0.39
    down
    0.38
     пишу
    0.38
     launchers
    0.38
    POSITIVE LOGITS
     extensão
    0.43
     Extension
    0.42
     extension
    0.40
     tartal
    0.39
     centra
    0.37
     updatedAt
    0.37
     Opera
    0.35
    Extension
    0.34
    ertation
    0.34
     ఆల
    0.34
    Act Density 0.000%

    No Known Activations