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

    Neuronpedia

    INDEX
    Explanations

    revealing information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     puro
    -0.08
     పరుగ
    -0.08
    ledes
    -0.08
     Joseph
    -0.07
     रन
    -0.07
     ಗಮನ
    -0.07
     गौर
    -0.07
     Shooting
    -0.07
    wegs
    -0.07
    Ż
    -0.07
    POSITIVE LOGITS
     responsibly
    0.10
     kepada
    0.09
     કરવાની
    0.09
     кому
    0.08
     willingly
    0.08
     করার
    0.08
     voluntarily
    0.08
    给
    0.08
    出去
    0.08
    多少
    0.08
    Act Density 0.031%

    No Known Activations