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

    Neuronpedia

    INDEX
    Explanations

    command words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    unted
    -0.08
     customs
    -0.07
     внут
    -0.07
    ज
    -0.07
     Torch
    -0.07
    	java
    -0.07
     Regards
    -0.06
     Jonah
    -0.06
    (list
    -0.06
    Java
    -0.06
    POSITIVE LOGITS
    ッカー
    0.07
    irectional
    0.06
    "urls
    0.06
     помощ
    0.06
     BAB
    0.06
    -relative
    0.06
    ordin
    0.06
    уск
    0.06
    ionario
    0.06
    hoa
    0.05
    Act Density 0.068%

    No Known Activations