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

    Neuronpedia

    INDEX
    Explanations

    roof

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Petrol
    -0.09
    _INFORMATION
    -0.08
     petrol
    -0.08
     нест
    -0.08
     ISBN
    -0.08
     hashtags
    -0.08
     locality
    -0.07
     journalism
    -0.07
     invaluable
    -0.07
     meticulous
    -0.07
    POSITIVE LOGITS
     deficiency
    0.09
     muc
    0.08
    moid
    0.08
    ilim
    0.08
     Ceiling
    0.08
     divider
    0.08
     vaulted
    0.08
     वेबस
    0.08
    drug
    0.07
     berb
    0.07
    Act Density 0.005%

    No Known Activations