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

    Neuronpedia

    INDEX
    Explanations

    sequences of whitespace characters

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

    code structure and data formats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     faſt
    -1.02
     ſta
    -0.98
     Administrativna
    -0.94
     للمعارف
    -0.91
     houſe
    -0.89
     ſche
    -0.88
     ſte
    -0.88
     Houſe
    -0.88
     Verſ
    -0.88
    ſelf
    -0.86
    POSITIVE LOGITS
     
    0.49
            
    0.39
    1
    0.38
        
    0.37
     $
    0.35
    The
    0.34
    2
    0.34
    3
    0.33
          
    0.33
     The
    0.33
    Act Density 0.005%

    No Known Activations