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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ěl
    -0.07
     कन
    -0.06
     coron
    -0.06
    back
    -0.06
     gad
    -0.06
     dried
    -0.06
    -right
    -0.06
    proper
    -0.06
     Dit
    -0.06
     BACK
    -0.06
    POSITIVE LOGITS
     알아
    0.07
    (credentials
    0.06
     hầu
    0.06
    
    0.06
    违
    0.06
     مقدم
    0.06
    续
    0.06
     uncomment
    0.06
     ajust
    0.06
     meilleurs
    0.06
    Act Density 0.006%

    No Known Activations