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

    Neuronpedia

    INDEX
    Explanations

    growth and learning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ispens
    -0.07
    urities
    -0.07
     hemisphere
    -0.07
    品质
    -0.07
    ú
    -0.07
     isp
    -0.06
    insula
    -0.06
    eds
    -0.06
    _UNKNOWN
    -0.06
    .setMinimum
    -0.06
    POSITIVE LOGITS
    竘
    0.07
     Peyton
    0.07
    .Connection
    0.07
     dictionaryWith
    0.07
     Malone
    0.07
     '../../../
    0.06
    تعب
    0.06
    Agent
    0.06
    两年
    0.06
    ༼
    0.06
    Act Density 0.024%

    No Known Activations