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
     afore
    -0.07
    XF
    -0.06
    .getMap
    -0.06
     measurable
    -0.06
    uce
    -0.06
    士
    -0.06
     fractures
    -0.06
     Cliff
    -0.06
    Formatted
    -0.06
    abbage
    -0.06
    POSITIVE LOGITS
    átek
    0.06
     tok
    0.06
     pomáh
    0.06
     struggling
    0.06
    ilight
    0.06
    ACHER
    0.06
    oliday
    0.06
    (tweet
    0.06
     bp
    0.06
     Branch
    0.05
    Act Density 0.004%

    No Known Activations