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

    Neuronpedia

    INDEX
    Explanations

    categorization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    شاء
    -0.07
     Meyer
    -0.07
     Happiness
    -0.07
     rew
    -0.06
     neurotrans
    -0.06
    	search
    -0.06
     fo
    -0.06
     amb
    -0.06
    Feed
    -0.06
    _logout
    -0.06
    POSITIVE LOGITS
     Slee
    0.06
     "${
    0.06
    (bounds
    0.06
     disturbances
    0.06
    ”:
    0.06
    .oauth
    0.06
    findViewById
    0.06
    キ
    0.06
     �
    0.06
     různých
    0.06
    Act Density 0.033%

    No Known Activations