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

    Neuronpedia

    INDEX
    Explanations

    }

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     implementation
    -0.07
    )은
    -0.07
     mart
    -0.07
    \"]
    -0.07
    }>{
    -0.06
    /utils
    -0.06
     warmer
    -0.06
     BlackBerry
    -0.06
    @hotmail
    -0.06
    _tracks
    -0.06
    POSITIVE LOGITS
    Monthly
    0.07
     내가
    0.07
     πε
    0.07
    uevo
    0.06
    カ
    0.06
    bag
    0.06
    �
    0.06
    facet
    0.06
    ‹
    0.06
    [vi
    0.06
    Act Density 0.003%

    No Known Activations