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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    $$$
    -0.08
    宜居
    -0.07
    ">\
    -0.07
     inert
    -0.07
    -ring
    -0.07
    เย
    -0.07
    速率
    -0.07
    쫄
    -0.07
    ポ
    -0.06
    -sur
    -0.06
    POSITIVE LOGITS
     guarantees
    0.07
     olds
    0.07
     collar
    0.07
     Collector
    0.07
     arena
    0.06
    0.06
     Orleans
    0.06
    敕
    0.06
     traumat
    0.06
    CLAIM
    0.06
    Act Density 0.002%

    No Known Activations