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

    Neuronpedia

    INDEX
    Explanations

    response or respond

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LOGGER
    1.07
    zonych
    0.98
    ع
    0.97
    ductors
    0.95
    нкт
    0.92
     زاويه
    0.90
    ර
    0.89
    리티
    0.89
    傛
    0.89
    জন্য
    0.89
    POSITIVE LOGITS
    𝟏
    1.05
    nse
    1.00
     urge
    0.99
    ственный
    0.99
    দেহ
    0.98
     chimique
    0.97
     ಪ್ಯಾ
    0.97
    ive
    0.97
     contient
    0.97
    Deposito
    0.97
    Act Density 0.231%

    No Known Activations