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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     storyteller
    -0.09
     narrator
    -0.08
    Yesterday
    -0.08
    Delivered
    -0.08
    inas
    -0.08
     Lect
    -0.08
    izas
    -0.08
     entregar
    -0.08
    Lect
    -0.08
    (Keys
    -0.08
    POSITIVE LOGITS
    _inside
    0.09
     внутри
    0.09
     inside
    0.09
     ভিত
    0.08
    .*?)
    0.08
     )
    0.08
    KE
    0.08
    0.08
    keh
    0.07
    ঠ
    0.07
    Act Density 0.028%
    No Known Activations