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

    Neuronpedia

    INDEX
    Explanations

    pseudonym

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    plets
    -0.06
     racing
    -0.06
    OperationException
    -0.06
     �
    -0.06
     Hazard
    -0.06
    аран
    -0.06
     соврем
    -0.06
    Hover
    -0.06
     replay
    -0.06
    ppo
    -0.06
    POSITIVE LOGITS
    .policy
    0.07
     assass
    0.07
    onyms
    0.07
     TERMS
    0.06
    螺
    0.06
     Boeh
    0.06
    empresa
    0.06
    contained
    0.06
    Equipment
    0.06
    /database
    0.06
    Act Density 0.004%

    No Known Activations