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

    Neuronpedia

    INDEX
    Explanations

    Rome

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Realty
    -0.08
    encrypted
    -0.07
    _priority
    -0.07
     đình
    -0.07
     always
    -0.07
     SECURITY
    -0.07
    льт
    -0.07
    past
    -0.07
     authToken
    -0.06
    iação
    -0.06
    POSITIVE LOGITS
     measurable
    0.07
    [url
    0.07
    ibir
    0.07
     museum
    0.07
    词汇
    0.06
    tons
    0.06
     Representation
    0.06
     dirs
    0.06
    .si
    0.06
     Acts
    0.06
    Act Density 0.029%

    No Known Activations