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
    Hip
    -0.07
    Blend
    -0.07
     Fer
    -0.07
    Pot
    -0.06
     racked
    -0.06
    ylv
    -0.06
    ettes
    -0.06
    Receipt
    -0.06
     patches
    -0.06
    _spi
    -0.06
    POSITIVE LOGITS
     strengthens
    0.07
    GNU
    0.07
    }';↵
    0.06
    áln
    0.06
    ilmiş
    0.06
    structure
    0.06
     './../../
    0.06
    }`)↵
    0.06
    ifications
    0.06
    );}↵↵
    0.06
    Act Density 0.009%

    No Known Activations