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

    Neuronpedia

    INDEX
    Explanations

    developed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Syracuse
    -0.07
     significant
    -0.07
     integerValue
    -0.07
    )),
    -0.06
    ../../
    -0.06
    mPid
    -0.06
     спри
    -0.06
    pute
    -0.06
    .prot
    -0.06
     út
    -0.06
    POSITIVE LOGITS
     COMM
    0.07
    ueil
    0.07
    rası
    0.06
    ackson
    0.06
    esi
    0.06
     Atatürk
    0.06
     sn
    0.06
    NAV
    0.06
     rust
    0.06
    abbix
    0.06
    Act Density 0.025%

    No Known Activations