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

    Neuronpedia

    INDEX
    Explanations

    Kannada language and culture

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     heuristic
    -0.07
     hạt
    -0.07
     ин
    -0.06
     brib
    -0.06
    进行
    -0.06
    adores
    -0.06
     penalties
    -0.06
     euros
    -0.06
    (chain
    -0.06
    ану
    -0.06
    POSITIVE LOGITS
     Clo
    0.08
    Located
    0.07
    _SECURE
    0.07
    jabi
    0.07
     Gujar
    0.07
    _follow
    0.07
    ulong
    0.07
     Filipino
    0.07
    umont
    0.06
     atheist
    0.06
    Act Density 0.006%

    No Known Activations