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

    Neuronpedia

    INDEX
    Explanations

    mechanical/industrial processes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Forget
    -0.08
     fraud
    -0.08
    隐藏
    -0.07
     fullscreen
    -0.07
     bán
    -0.07
     activists
    -0.07
     Fraud
    -0.07
     remembered
    -0.06
    .Remote
    -0.06
    _UART
    -0.06
    POSITIVE LOGITS
    izzard
    0.07
     ',
    0.07
    ога
    0.06
    .i
    0.06
    GRADE
    0.06
    caf
    0.06
    proj
    0.06
     jj
    0.06
     renaming
    0.06
     SI
    0.05
    Act Density 0.078%

    No Known Activations