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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    solete
    -0.07
    Handler
    -0.07
    规
    -0.07
    арі
    -0.06
    Notifier
    -0.06
     đạt
    -0.06
     Bayern
    -0.06
    те
    -0.06
     яке
    -0.06
     literal
    -0.06
    POSITIVE LOGITS
    ESA
    0.07
     removable
    0.06
    _FC
    0.06
    	me
    0.06
     Opening
    0.06
    Minutes
    0.06
    _Label
    0.06
    Metrics
    0.06
    ่าจะ
    0.06
    Gam
    0.06
    Act Density 0.044%

    No Known Activations