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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.06
     �
    -0.06
     khẳng
    -0.06
    .mode
    -0.06
    .keySet
    -0.06
    .nl
    -0.06
     країн
    -0.06
     pathMatch
    -0.06
    �
    -0.06
    matchCondition
    -0.06
    POSITIVE LOGITS
     of
    0.07
     composer
    0.06
     sisters
    0.06
     protests
    0.06
     former
    0.06
     preferred
    0.06
    }
    0.06
    Anything
    0.06
     alla
    0.06
     ROCK
    0.06
    Act Density 0.028%

    No Known Activations