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

    Neuronpedia

    INDEX
    Explanations

    left

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
      
    0.78
    {
    0.70
     {
    0.68
    ");
    0.64
     true
    0.61
    accion
    0.60
     tra
    0.59
    ["
    0.58
     "_
    0.57
     procede
    0.57
    POSITIVE LOGITS
    antiene
    0.96
     -!
    0.92
    multline
    0.90
    ।*
    0.90
    âns
    0.90
    ].”
    0.90
    <unused169>
    0.88
    bullying
    0.88
    ittura
    0.87
     Alyssa
    0.87
    Act Density 0.001%

    No Known Activations