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

    Neuronpedia

    INDEX
    Explanations

    loose

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ഗ
    -0.09
    bbc
    -0.08
    rij
    -0.08
     nghiệm
    -0.08
    രിച്ചു
    -0.08
    iname
    -0.08
    ুম
    -0.08
    иру
    -0.08
    ാധ
    -0.08
    رج
    -0.08
    POSITIVE LOGITS
     फेर
    0.08
     प्रेस
    0.07
     pous
    0.07
     homepage
    0.07
     manuscript
    0.07
     assumir
    0.07
     domicilio
    0.07
     porch
    0.07
     Foss
    0.07
     underlying
    0.07
    Act Density 0.004%

    No Known Activations