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

    Neuronpedia

    INDEX
    Explanations

    reasons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     packing
    -0.08
     pretty
    -0.07
     grid
    -0.07
     About
    -0.07
     Sodium
    -0.07
     removal
    -0.07
     plate
    -0.07
     Removal
    -0.07
     damage
    -0.07
     sodium
    -0.07
    POSITIVE LOGITS
     Cobra
    0.06
    _alias
    0.06
    IRM
    0.06
    exc
    0.05
     Intermediate
    0.05
     asynchronously
    0.05
    rowse
    0.05
     aby
    0.05
     đứng
    0.05
     ceasefire
    0.05
    Act Density 0.043%

    No Known Activations