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

    Neuronpedia

    INDEX
    Explanations

    code blocks and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    i
    0.53
    ↵
    0.50
    u
    0.49
    id
    0.46
        
    0.45
     i
    0.45
    x
    0.45
    io
    0.43
    us
    0.42
    0.41
    POSITIVE LOGITS
     protéines
    0.45
    RAchievement
    0.41
    Prothorax
    0.40
     vaginale
    0.40
     antibiot
    0.40
     prostagland
    0.39
     carbohyd
    0.39
     cytok
    0.39
    Pyrazole
    0.39
     diarrh
    0.39
    Act Density 0.026%

    No Known Activations