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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DOG
    -0.06
     �
    -0.06
    .xmlbeans
    -0.06
     tasarım
    -0.06
     keyst
    -0.06
    tram
    -0.06
    thro
    -0.06
    �示
    -0.06
    .ylim
    -0.06
     Courier
    -0.06
    POSITIVE LOGITS
    .Ed
    0.07
     embarrass
    0.07
     Sof
    0.07
    itating
    0.07
    ourage
    0.06
     πο
    0.06
     Mult
    0.06
     annoying
    0.06
    ziej
    0.06
     TBranch
    0.06
    Act Density 0.262%

    No Known Activations