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

    Neuronpedia

    INDEX
    Explanations

    technical concepts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    西省
    -0.07
    �
    -0.07
     fais
    -0.06
    歌
    -0.06
     Avery
    -0.06
    Swagger
    -0.06
     Zuckerberg
    -0.06
     dalam
    -0.06
    historic
    -0.06
    ámara
    -0.06
    POSITIVE LOGITS
     }}"
    0.06
    	config
    0.06
     Bot
    0.06
     negotiate
    0.06
    liches
    0.06
    OLS
    0.06
    생활
    0.06
     oh
    0.06
     illustrations
    0.06
    ('$
    0.06
    Act Density 0.421%

    No Known Activations