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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Detailed
    -0.07
     traveller
    -0.06
     الأسر
    -0.06
    Mvc
    -0.06
    BW
    -0.06
     Belg
    -0.06
     VLAN
    -0.06
     travellers
    -0.06
    OE
    -0.06
    alar
    -0.06
    POSITIVE LOGITS
     avent
    0.07
    lust
    0.07
    ắm
    0.07
    ETYPE
    0.07
     glacier
    0.07
     =============================================================================↵
    0.06
    __':↵
    0.06
     중심
    0.06
    ọt
    0.06
    RAD
    0.06
    Act Density 0.020%

    No Known Activations