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

    Neuronpedia

    INDEX
    Explanations

    explain hypothetical scenarios

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    䏼
    0.98
    㫻
    0.94
    陖
    0.94
    Antes
    0.92
    OfThe
    0.92
    楇
    0.92
    AutorLabel
    0.91
    Ά
    0.91
    ibacter
    0.90
    ቕ
    0.90
    POSITIVE LOGITS
      
    0.94
     also
    0.81
     and
    0.78
    dit
    0.78
     again
    0.74
     likewise
    0.73
     or
    0.72
     similarly
    0.72
     های
    0.71
     the
    0.71
    Act Density 1.467%

    No Known Activations