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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SSI
    -0.07
    _producto
    -0.06
    	cli
    -0.06
    (itr
    -0.06
     khả
    -0.06
    policy
    -0.06
     thức
    -0.06
    ripple
    -0.06
    SOAP
    -0.06
    商品
    -0.06
    POSITIVE LOGITS
    "))
↵
    0.06
     ζω
    0.06
     Pentagon
    0.06
    μπο
    0.06
    (list
    0.06
     Crit
    0.06
    :+
    0.06
    ost
    0.06
     populated
    0.06
     dream
    0.06
    Act Density 0.002%

    No Known Activations