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

    Neuronpedia

    INDEX
    Explanations

    math expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Level
    -0.07
    mates
    -0.07
     por
    -0.07
     trabajado
    -0.07
     workplaces
    -0.07
    jections
    -0.07
     participado
    -0.07
     claros
    -0.07
     معهم
    -0.07
     tal
    -0.06
    POSITIVE LOGITS
     suprem
    0.10
    无限
    0.10
     zen
    0.09
     insanity
    0.09
     hinweg
    0.09
     цены
    0.09
     extrema
    0.09
     greatness
    0.09
     supreme
    0.09
     ekstrem
    0.09
    Act Density 0.049%

    No Known Activations