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

    Neuronpedia

    INDEX
    Explanations

    coding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ेलन
    -0.08
     unpleasant
    -0.08
     regional
    -0.08
    Regional
    -0.08
    Driving
    -0.08
    'électricité
    -0.08
     irritating
    -0.08
     fasting
    -0.08
    Opening
    -0.08
     melhorar
    -0.08
    POSITIVE LOGITS
    复制
    0.18
     clone
    0.17
     copying
    0.17
     Clone
    0.17
    コピー
    0.17
     copy
    0.16
     copies
    0.16
     Copies
    0.16
     Copy
    0.16
     deepcopy
    0.16
    Act Density 0.007%

    No Known Activations