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

    Neuronpedia

    INDEX
    Explanations

    last

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    isers
    -0.06
    FUNCTION
    -0.06
    ENTIC
    -0.06
     gute
    -0.06
     apolog
    -0.06
    $.
    -0.05
     fins
    -0.05
     early
    -0.05
    _WATER
    -0.05
     ease
    -0.05
    POSITIVE LOGITS
    óż
    0.07
     Donetsk
    0.07
    .kernel
    0.07
    	SC
    0.06
    enn
    0.06
    ://"
    0.06
    QueryBuilder
    0.06
    leen
    0.06
     Gathering
    0.06
    ังน
    0.06
    Act Density 0.138%

    No Known Activations