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

    Neuronpedia

    INDEX
    Explanations

    key

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Hat
    -0.07
     notion
    -0.07
    (icon
    -0.07
     locality
    -0.06
    _space
    -0.06
    -weight
    -0.06
     července
    -0.06
    -fr
    -0.06
     evasion
    -0.06
     Moreno
    -0.06
    POSITIVE LOGITS
    Anonymous
    0.07
    治
    0.07
    ilver
    0.06
    کیل
    0.06
     manageable
    0.06
    	constructor
    0.06
     ADDR
    0.06
     '/')↵
    0.06
     Imports
    0.06
    ifie
    0.06
    Act Density 0.005%

    No Known Activations