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

    Neuronpedia

    INDEX
    Explanations

    HTML code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mamma
    -0.06
    standing
    -0.06
     Poke
    -0.06
    ंपर
    -0.06
     Bot
    -0.06
    _VAL
    -0.06
     розвитку
    -0.06
     koje
    -0.06
     honey
    -0.06
    ably
    -0.06
    POSITIVE LOGITS
     ounce
    0.08
    }}"
    0.08
    위원
    0.07
    iyeti
    0.07
    )),↵
    0.07
    oseconds
    0.07
    _desc
    0.07
    {}]
    0.07
     },↵
    0.07
    iд
    0.06
    Act Density 0.112%

    No Known Activations