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

    Neuronpedia

    INDEX
    Explanations

    Animal testing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    售
    -0.07
    SIM
    -0.07
     malloc
    -0.07
    效
    -0.07
    走
    -0.07
    temps
    -0.07
     :'
    -0.07
     Explosion
    -0.06
    _All
    -0.06
    君
    -0.06
    POSITIVE LOGITS
     cx
    0.06
     redis
    0.06
     пля
    0.06
     unsupported
    0.06
     segundos
    0.06
     dus
    0.06
     abs
    0.06
    pre
    0.06
    .syn
    0.06
     appealing
    0.06
    Act Density 0.016%

    No Known Activations