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

    Neuronpedia

    INDEX
    Explanations

    ion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ӯ
    -0.07
     universally
    -0.07
    .stride
    -0.07
    spe
    -0.07
    ，《
    -0.07
     WHETHER
    -0.06
    ."
    -0.06
    .Decode
    -0.06
     hearing
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     bigotry
    0.08
    考え方
    0.07
    远景
    0.07
     psychic
    0.07
     policing
    0.07
     monitors
    0.07
    زين
    0.07
     Superior
    0.07
    넬
    0.06
    淀
    0.06
    Act Density 0.001%

    No Known Activations