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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fromDate
    -0.07
    LinkedList
    -0.06
    _blocks
    -0.06
     mek
    -0.06
    resp
    -0.06
    (access
    -0.06
     soaked
    -0.06
     Wer
    -0.06
    't
    -0.05
    (temp
    -0.05
    POSITIVE LOGITS
     Pluto
    0.08
    ');?>↵
    0.07
    -Benz
    0.07
    pac
    0.07
     ]]
    0.06
    ").↵
    0.06
     tighten
    0.06
     الل
    0.06
     phí
    0.06
    .");
↵
    0.06
    Act Density 0.004%

    No Known Activations