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

    Neuronpedia

    INDEX
    Explanations

    SH

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Palo
    -0.07
    ать
    -0.07
     invaded
    -0.07
    .partition
    -0.06
     forecasts
    -0.06
     берем
    -0.06
    anela
    -0.06
     imposed
    -0.06
     Eventually
    -0.06
     então
    -0.06
    POSITIVE LOGITS
    习
    0.07
    ={!
    0.07
    ＿_
    0.06
     stř
    0.06
     CHARSET
    0.06
    ($(".
    0.06
    ΙΚΗ
    0.06
    slow
    0.06
    romise
    0.06
    Inlining
    0.06
    Act Density 0.001%

    No Known Activations