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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .nodeName
    -0.07
     merry
    -0.07
     lett
    -0.07
     fancy
    -0.07
    tones
    -0.07
     aria
    -0.07
     filetype
    -0.07
    黠
    -0.07
    调皮
    -0.06
    管理条例
    -0.06
    POSITIVE LOGITS
     Crush
    0.09
     grandmother
    0.08
     costing
    0.07
    izard
    0.07
     linker
    0.07
    勺
    0.07
     THESE
    0.07
    color
    0.07
     Consumer
    0.07
    aze
    0.07
    Act Density 0.013%

    No Known Activations