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

    Neuronpedia

    INDEX
    Explanations

    Fairy tales

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Miles
    -0.07
     sunk
    -0.07
     leagues
    -0.06
     known
    -0.06
     Hiệp
    -0.06
     hỗ
    -0.06
    湯
    -0.06
    Cover
    -0.06
    ička
    -0.06
    のか
    -0.06
    POSITIVE LOGITS
    /inet
    0.07
     Tiny
    0.07
     ctrl
    0.06
    	fmt
    0.06
     conscience
    0.06
    exec
    0.06
    unist
    0.06
     直
    0.06
     Panc
    0.06
     могут
    0.06
    Act Density 0.004%

    No Known Activations