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

    Neuronpedia

    INDEX
    Explanations

    contains

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _vc
    -0.07
     ['',
    -0.06
    {}'.
    -0.06
    '=>['
    -0.06
     stencil
    -0.06
    -0.06
     UCS
    -0.06
     ภาพ
    -0.06
    Say
    -0.06
     sant
    -0.06
    POSITIVE LOGITS
     inspiration
    0.07
     soy
    0.06
    elmet
    0.06
    CORD
    0.06
     */
↵
↵
↵
    0.06
     carefully
    0.06
    <Article
    0.06
     дых
    0.06
    ент
    0.06
    ANDING
    0.06
    Act Density 0.000%

    No Known Activations