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

    Neuronpedia

    INDEX
    Explanations

    digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    anny
    -0.08
    classes
    -0.07
     Maybe
    -0.07
     mapping
    -0.07
     tom
    -0.07
     leur
    -0.07
    genes
    -0.07
     course
    -0.07
     Lap
    -0.07
     Abbey
    -0.07
    POSITIVE LOGITS
    一回事
    0.07
     ('\
    0.07
    ことがある
    0.07
    (code
    0.07
     medications
    0.07
     molecule
    0.06
    matter
    0.06
    调查显示
    0.06
    Quantity
    0.06
    征收
    0.06
    Act Density 0.005%

    No Known Activations