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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     будів
    -0.07
     screwed
    -0.06
     cavity
    -0.06
    iors
    -0.06
    üyük
    -0.06
     unloaded
    -0.06
    -fields
    -0.06
     yaptık
    -0.06
    	socket
    -0.06
     showing
    -0.06
    POSITIVE LOGITS
     औ
    0.07
     تازه
    0.06
     Burl
    0.06
    /an
    0.06
     aides
    0.06
    .iteritems
    0.06
    exampleInputEmail
    0.06
    _DEPRECATED
    0.06
     relie
    0.06
    *S
    0.06
    Act Density 0.108%

    No Known Activations