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

    Neuronpedia

    INDEX
    Explanations

    Describes actions or states of being

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	code
    -0.07
    ")}↵
    -0.07
    .partition
    -0.07
     Enabled
    -0.06
     fetchData
    -0.06
    _unknown
    -0.06
     Restart
    -0.06
     },
    -0.06
     treasurer
    -0.06
     Rew
    -0.06
    POSITIVE LOGITS
     cute
    0.07
    xic
    0.06
     kuk
    0.06
    LOAD
    0.06
    _Price
    0.06
     noss
    0.06
    	sound
    0.06
    ्रण
    0.06
    かな
    0.06
    removeClass
    0.06
    Act Density 0.237%

    No Known Activations