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

    Neuronpedia

    INDEX
    Explanations

    single quote

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Olympic
    -0.07
     Mexico
    -0.07
     Creek
    -0.07
    Å
    -0.06
    	pos
    -0.06
     stretches
    -0.06
     있어
    -0.06
     maintenant
    -0.06
    _thr
    -0.06
     Fritz
    -0.06
    POSITIVE LOGITS
     versatility
    0.07
     söyledi
    0.06
     gül
    0.06
     plast
    0.06
    _gchandle
    0.06
     believes
    0.06
    Alternatively
    0.06
     etraf
    0.06
    สถานท
    0.06
    acje
    0.06
    Act Density 0.020%

    No Known Activations