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

    Neuronpedia

    INDEX
    Explanations

    Code/Vulnerability related

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    \R
    -0.07
     MainAxisAlignment
    -0.07
     readline
    -0.06
    >Name
    -0.06
     ATH
    -0.06
     игра
    -0.06
    917
    -0.06
     RH
    -0.06
     attrib
    -0.06
     fortunes
    -0.06
    POSITIVE LOGITS
    OO
    0.07
     Loud
    0.07
    -safe
    0.07
     무료
    0.06
    .getS
    0.06
    -append
    0.06
    oo
    0.06
     samozřejmě
    0.06
     stejně
    0.06
    _COUNT
    0.06
    Act Density 1.285%

    No Known Activations