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

    Neuronpedia

    INDEX
    Explanations

    control

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    avored
    -0.07
    .SuppressLint
    -0.07
     mænd
    -0.06
     rampage
    -0.06
     here
    -0.06
    _lines
    -0.06
    IELDS
    -0.06
    seen
    -0.06
     amazed
    -0.06
    dee
    -0.06
    POSITIVE LOGITS
     control
    0.10
     Control
    0.09
    control
    0.09
     CONTROL
    0.08
    Control
    0.07
    cstdint
    0.07
     hồ
    0.07
    ueue
    0.07
    boolean
    0.06
     steril
    0.06
    Act Density 0.026%

    No Known Activations