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

    Neuronpedia

    INDEX
    Explanations

    glad

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     telesc
    -0.08
     fourn
    -0.07
    -0.07
     FOUND
    -0.07
     appearances
    -0.07
    ](↵
    -0.06
    overwrite
    -0.06
    overn
    -0.06
    	Write
    -0.06
     псих
    -0.06
    POSITIVE LOGITS
     glad
    0.10
     Glad
    0.08
    ��
    0.07
     Auxiliary
    0.07
    Benefits
    0.07
     nodeList
    0.07
     comparing
    0.06
    pard
    0.06
     Lloyd
    0.06
    Loss
    0.06
    Act Density 0.003%

    No Known Activations