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

    Neuronpedia

    INDEX
    Explanations

    internal detail

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     millennia
    -0.08
    _approx
    -0.07
     FALSE
    -0.07
     TRUE
    -0.06
    Enumeration
    -0.06
     coffin
    -0.06
    井
    -0.06
     Caucas
    -0.06
     amp
    -0.06
    ­i
    -0.06
    POSITIVE LOGITS
    committee
    0.06
    result
    0.06
    ories
    0.06
    purple
    0.06
    rollback
    0.06
    40
    0.06
    comes
    0.06
    profits
    0.06
    dock
    0.06
    _HW
    0.06
    Act Density 0.005%

    No Known Activations