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

    Neuronpedia

    INDEX
    Explanations

    told

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ignite
    -0.07
    政
    -0.07
    няют
    -0.06
    _atom
    -0.06
     acceptance
    -0.06
    Total
    -0.06
    enties
    -0.06
    otide
    -0.06
    _ACK
    -0.06
     Exc
    -0.06
    POSITIVE LOGITS
     Savannah
    0.07
    ωμα
    0.06
    Reload
    0.06
    MATCH
    0.06
    'all
    0.06
     шлях
    0.06
    (current
    0.06
     درس
    0.06
    社會
    0.06
     potentials
    0.06
    Act Density 0.029%

    No Known Activations