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

    Neuronpedia

    INDEX
    Explanations

    narrations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Manchester
    -0.07
    	writel
    -0.07
    Stmt
    -0.07
    _fitness
    -0.06
    ennai
    -0.06
    álo
    -0.06
     propre
    -0.06
     unst
    -0.06
    クト
    -0.06
    isque
    -0.06
    POSITIVE LOGITS
    
    0.06
    意味
    0.06
    (fig
    0.06
     ideological
    0.06
    (confirm
    0.06
     denim
    0.06
     paintings
    0.06
    -inspired
    0.06
     talked
    0.06
     adjusting
    0.06
    Act Density 0.066%

    No Known Activations