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

    Neuronpedia

    INDEX
    Explanations

    ila

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Trem
    -0.06
     Nak
    -0.06
    ném
    -0.06
     sever
    -0.06
     Anc
    -0.06
    ,std
    -0.06
    (sess
    -0.06
     Inputs
    -0.06
     Ra
    -0.06
    ़्
    -0.06
    POSITIVE LOGITS
     spills
    0.07
    ustainability
    0.07
    opi
    0.06
     kolay
    0.06
    rella
    0.06
    ussian
    0.06
     широк
    0.06
    们
    0.06
    onents
    0.06
     skon
    0.06
    Act Density 0.003%

    No Known Activations