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

    Neuronpedia

    INDEX
    Explanations

    asterisk

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -existent
    -0.07
     solving
    -0.06
     room
    -0.06
    €“
    -0.06
     fog
    -0.06
    Printing
    -0.06
      
    -0.06
     Bình
    -0.06
     pearl
    -0.06
     vans
    -0.06
    POSITIVE LOGITS
    (fid
    0.07
    モ
    0.07
     شامل
    0.06
    .Mockito
    0.06
    態
    0.06
     ماه
    0.06
     enqu
    0.06
    也有
    0.06
     stál
    0.06
     благодаря
    0.06
    Act Density 0.000%

    No Known Activations