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

    Neuronpedia

    INDEX
    Explanations

    something divided

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    `↵
    -0.06
    artist
    -0.06
     naam
    -0.06
     occur
    -0.06
    grams
    -0.06
    Attention
    -0.06
     ＼↵
    -0.05
     giúp
    -0.05
     importante
    -0.05
    []
↵
    -0.05
    POSITIVE LOGITS
    .iterator
    0.07
    fol
    0.07
    although
    0.06
     plead
    0.06
     CCTV
    0.06
    eden
    0.06
     DOUBLE
    0.06
     οικο
    0.06
    _HALF
    0.06
     HAL
    0.06
    Act Density 0.022%

    No Known Activations