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

    Neuronpedia

    INDEX
    Explanations

    9

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    平方公里
    -0.07
    .Black
    -0.07
     Estonia
    -0.07
     components
    -0.07
    _ignore
    -0.07
     میشود
    -0.06
     листопада
    -0.06
    фра
    -0.06
     yazı
    -0.06
    _CAST
    -0.06
    POSITIVE LOGITS
    (enum
    0.06
    /post
    0.06
    reward
    0.06
     neoliberal
    0.06
     nominees
    0.06
     edeb
    0.06
     elusive
    0.06
    gap
    0.06
     Vườn
    0.06
     dv
    0.06
    Act Density 0.001%

    No Known Activations