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

    Neuronpedia

    INDEX
    Explanations

    Code/Programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     имеют
    -0.07
    保
    -0.07
    apos
    -0.06
    และ
    -0.06
    -rounded
    -0.06
     aboard
    -0.06
     McDon
    -0.06
     //////////////////////////////////
    -0.06
     змін
    -0.06
    .vstack
    -0.06
    POSITIVE LOGITS
    ator
    0.07
    ©©
    0.07
    -update
    0.07
     enclave
    0.07
     акт
    0.06
    voir
    0.06
    lay
    0.06
    /Public
    0.06
     siti
    0.06
     complaining
    0.06
    Act Density 0.025%

    No Known Activations