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

    Neuronpedia

    INDEX
    Explanations

    evaluation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     investigated
    -0.08
     העיר
    -0.07
    细则
    -0.07
     Hom
    -0.07
     LED
    -0.07
    꺠
    -0.06
     CEOs
    -0.06
    -labelled
    -0.06
     grö
    -0.06
    人と
    -0.06
    POSITIVE LOGITS
     cort
    0.07
    (previous
    0.07
    -output
    0.07
    勃
    0.07
    ritch
    0.07
    atables
    0.07
    🇦
    0.07
    apas
    0.06
    价格上涨
    0.06
    ":-
    0.06
    Act Density 0.079%

    No Known Activations