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

    Neuronpedia

    INDEX
    Explanations

    encoded strings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _configuration
    -0.08
     assertFalse
    -0.07
    	Il
    -0.07
     versus
    -0.07
    _preferences
    -0.07
    (startTime
    -0.07
     insists
    -0.07
    ampionship
    -0.07
     Cue
    -0.07
     Dustin
    -0.06
    POSITIVE LOGITS
    建成后
    0.07
    솨
    0.07
    来看看吧
    0.07
     yaptığı
    0.07
     Parliamentary
    0.06
     noss
    0.06
    ⛩
    0.06
     진
    0.06
     hb
    0.06
    chron
    0.06
    Act Density 0.002%

    No Known Activations