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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (t
    -0.07
     dan
    -0.07
     feder
    -0.06
     Ting
    -0.06
     Restore
    -0.06
     wang
    -0.06
     sing
    -0.06
    střed
    -0.06
     '"
    -0.06
     remover
    -0.06
    POSITIVE LOGITS
    .places
    0.07
    \FrameworkBundle
    0.06
    (currentUser
    0.06
     meilleure
    0.06
    Y
    0.06
    lero
    0.06
    áln
    0.06
     disappointing
    0.06
    ЮЛ
    0.06
    YZ
    0.06
    Act Density 0.000%

    No Known Activations