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

    Neuronpedia

    INDEX
    Explanations

    comments and annotations in code or text

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

    C/C++ code with additions

    np_acts-logits-general · gemini-2.0-flash

    historical names and archaisms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nu
    -0.63
    etron
    -0.62
     qu
    -0.60
     gra
    -0.58
     te
    -0.57
     null
    -0.56
     chat
    -0.56
    ETTA
    -0.56
    etti
    -0.56
     Willis
    -0.55
    POSITIVE LOGITS
     Pompey
    0.92
        
    0.90
            
    0.85
    　　
    0.85
     Cæsar
    0.83
    0.82
     Shaksp
    0.82
          
    0.81
     theſe
    0.81
     ſeveral
    0.81
    Act Density 0.062%

    No Known Activations