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

    Neuronpedia

    INDEX
    Explanations

    publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Sorting
    -0.08
    overn
    -0.07
     Drug
    -0.07
    ド
    -0.07
     Analysis
    -0.07
     keto
    -0.07
     improv
    -0.07
    阅历
    -0.07
    辦
    -0.07
     scrambling
    -0.07
    POSITIVE LOGITS
    .false
    0.07
    _uint
    0.07
     Vertical
    0.07
    暑假
    0.07
    flush
    0.07
    𝔢
    0.07
     filmm
    0.06
     bronze
    0.06
    традицион
    0.06
    鹒
    0.06
    Act Density 0.032%

    No Known Activations