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

    Neuronpedia

    INDEX
    Explanations

    Anatomy, Physiology, -ology

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    que
    1.91
    ם
    1.86
    ו
    1.69
     sanitaria
    1.52
    ן
    1.46
    ità
    1.45
     veng
    1.43
    en
    1.41
    el
    1.34
    ۹
    1.32
    POSITIVE LOGITS
    те
    2.00
    ER
    1.73
    EM
    1.64
    PORTS
    1.52
     случаях
    1.46
    ία
    1.43
     ставак
    1.40
    OS
    1.39
    浔
    1.38
    EK
    1.37
    Act Density 0.311%

    No Known Activations