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

    Neuronpedia

    INDEX
    Explanations

    sequences of repeated characters or whitespace

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     desmotivaciones
    -0.94
     ſche
    -0.94
     queſta
    -0.92
     ſta
    -0.90
     indígen
    -0.85
     auroit
    -0.85
     pleaſure
    -0.84
     pouvoit
    -0.84
    ſelf
    -0.83
     avoient
    -0.83
    POSITIVE LOGITS
      
    0.79
    0.71
        
    0.65
       
    0.62
    The
    0.57
     a
    0.55
    O
    0.53
    I
    0.50
    　
    0.50
    YS
    0.49
    Act Density 0.005%

    No Known Activations