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

    Neuronpedia

    INDEX
    Explanations

    Dappled, detailed imagery

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    metrics
    -0.07
    μό
    -0.07
    melon
    -0.07
     gush
    -0.07
     puntu
    -0.07
    -export
    -0.07
     utd
    -0.07
    ouv
    -0.07
     independente
    -0.07
     competente
    -0.07
    POSITIVE LOGITS
     sunlight
    0.10
     shadows
    0.09
     sombras
    0.09
     വന
    0.08
     brown
    0.08
     Hawaiian
    0.08
     shadow
    0.08
     वन
    0.08
    遮
    0.07
    罩
    0.07
    Act Density 0.001%

    No Known Activations