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

    Neuronpedia

    INDEX
    Explanations

    Therefore

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    PBS
    -0.07
     Schn
    -0.07
    ρκεια
    -0.06
    ῆ
    -0.06
    formance
    -0.06
    _increment
    -0.06
    ,index
    -0.06
    ีฟ
    -0.06
    %@",
    -0.06
    Ascii
    -0.06
    POSITIVE LOGITS
     lep
    0.07
     screamed
    0.06
     yoksa
    0.06
     tutar
    0.06
    PGA
    0.06
     Verify
    0.06
     отли
    0.06
    �
    0.06
     Autumn
    0.06
     –↵
    0.06
    Act Density 0.011%

    No Known Activations