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

    Neuronpedia

    INDEX
    Explanations

    exclusively

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ५
    -0.08
     �
    -0.07
     هست
    -0.07
     ан
    -0.07
     notre
    -0.07
     dul
    -0.07
     wasted
    -0.07
     Beaut
    -0.07
     příjem
    -0.07
     BIND
    -0.06
    POSITIVE LOGITS
     Hav
    0.06
    rypto
    0.06
     coordinates
    0.06
    хови
    0.06
    uez
    0.06
     radio
    0.06
    _exists
    0.06
    TabIndex
    0.06
     frequencies
    0.06
     Saudis
    0.06
    Act Density 0.004%

    No Known Activations