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

    Neuronpedia

    INDEX
    Explanations

    web content/code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    カ
    -0.06
    ith
    -0.06
    ワ
    -0.06
    _half
    -0.06
    IRON
    -0.06
    婆
    -0.06
    ilet
    -0.06
    ('~
    -0.06
    ITH
    -0.06
    �y
    -0.06
    POSITIVE LOGITS
     одне
    0.07
     Alberto
    0.07
    .QueryString
    0.07
     Hibernate
    0.07
     oa
    0.06
    unable
    0.06
    */
↵
    0.06
     continents
    0.06
    Proceed
    0.06
     unable
    0.06
    Act Density 0.040%

    No Known Activations