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

    Neuronpedia

    INDEX
    Explanations

    k

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Alan
    -0.07
     Cuba
    -0.07
    /Typography
    -0.07
     Ukraine
    -0.06
     Computers
    -0.06
     Би
    -0.06
    	V
    -0.06
     También
    -0.06
    .patient
    -0.06
    COVID
    -0.06
    POSITIVE LOGITS
     hacking
    0.06
    �
    0.06
     згад
    0.06
    (compact
    0.06
    讨
    0.06
     kendine
    0.06
     enclave
    0.06
    AXB
    0.06
    惠
    0.06
     productive
    0.06
    Act Density 0.000%

    No Known Activations