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

    Neuronpedia

    INDEX
    Explanations

    sentence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Vương
    -0.07
     rotating
    -0.07
     Operation
    -0.07
    -degree
    -0.06
    _na
    -0.06
    _SCREEN
    -0.06
    ря
    -0.06
    _BOOL
    -0.06
     frames
    -0.06
     comprises
    -0.06
    POSITIVE LOGITS
    添
    0.06
    (forms
    0.06
     flawed
    0.06
    (":
    0.06
    онах
    0.06
     //
↵
↵
    0.06
    .Handled
    0.06
    ecome
    0.06
      ↵  ↵
    0.06
    avax
    0.06
    Act Density 0.003%

    No Known Activations