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

    Neuronpedia

    INDEX
    Explanations

    b

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    сылки
    -0.07
     Executors
    -0.07
     концеп
    -0.06
     αρι
    -0.06
    براير
    -0.06
    роиз
    -0.06
    케
    -0.06
    kses
    -0.06
    臣
    -0.06
    Whilst
    -0.06
    POSITIVE LOGITS
     carefully
    0.07
     injuries
    0.06
    (encoding
    0.06
     tweeting
    0.06
    _BASIC
    0.06
     waterfront
    0.06
     directory
    0.06
    Translator
    0.06
     rootNode
    0.06
    .person
    0.06
    Act Density 0.000%

    No Known Activations