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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _slider
    -0.07
    _hold
    -0.07
    edom
    -0.07
    _percentage
    -0.07
    -trash
    -0.07
    <D
    -0.07
     accustomed
    -0.07
    🐩
    -0.06
     CENTER
    -0.06
    适时
    -0.06
    POSITIVE LOGITS
    -builder
    0.07
    phe
    0.06
    xab
    0.06
     fifo
    0.06
    /
↵
    0.06
     ""));↵
    0.06
    提出的
    0.06
    rafted
    0.06
    chain
    0.06
     modelling
    0.06
    Act Density 0.003%

    No Known Activations