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

    Neuronpedia

    INDEX
    Explanations

    date and time code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	url
    -0.07
     caves
    -0.06
     Spatial
    -0.06
    	mask
    -0.06
     Reward
    -0.06
     elephant
    -0.06
     Ding
    -0.06
     scroll
    -0.06
     усі
    -0.05
    -shop
    -0.05
    POSITIVE LOGITS
    अ
    0.07
    annels
    0.07
    kých
    0.07
     задов
    0.07
    Returned
    0.06
    Already
    0.06
    Accessible
    0.06
    िछ
    0.06
    žení
    0.06
    usted
    0.06
    Act Density 0.142%

    No Known Activations