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

    Neuronpedia

    INDEX
    Explanations

    eh

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    izzie
    -0.08
    ncpy
    -0.07
    AtIndex
    -0.07
    äng
    -0.07
    ondheim
    -0.07
    	bg
    -0.07
     unto
    -0.07
    _grp
    -0.07
    _Grid
    -0.06
    𝕿
    -0.06
    POSITIVE LOGITS
     Walter
    0.07
     отлич
    0.07
    というのが
    0.07
     rapid
    0.07
     Richmond
    0.07
     мех
    0.07
    fetch
    0.06
    FROM
    0.06
    恰好
    0.06
    솬
    0.06
    Act Density 0.003%

    No Known Activations