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

    Neuronpedia

    INDEX
    Explanations

    Numerical comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    なんて
    -0.07
     emphas
    -0.06
    	RTE
    -0.06
     une
    -0.06
     Olsen
    -0.06
     بها
    -0.06
    _REGION
    -0.06
     США
    -0.06
    _contr
    -0.06
    ↵	↵
    -0.06
    POSITIVE LOGITS
     gerçekten
    0.06
    ally
    0.06
     wireless
    0.06
    ستانی
    0.06
     Grocery
    0.06
     Bones
    0.06
    том
    0.06
    LESS
    0.06
    ité
    0.06
    xd
    0.06
    Act Density 0.020%

    No Known Activations