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

    Neuronpedia

    INDEX
    Explanations

    Daniel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Single
    -0.07
     PF
    -0.07
    ophy
    -0.06
    Wifi
    -0.06
    veedor
    -0.06
    Proveedor
    -0.06
     explosives
    -0.06
     Shorts
    -0.06
    766
    -0.06
     Carnegie
    -0.06
    POSITIVE LOGITS
    Daniel
    0.09
     Daniel
    0.07
    ael
    0.07
     визначення
    0.07
    aniel
    0.07
    ีการ
    0.07
    /dd
    0.07
    炎
    0.07
    UAGE
    0.06
     ecs
    0.06
    Act Density 0.003%

    No Known Activations