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

    Neuronpedia

    INDEX
    Explanations

    output labels and results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    0.92
     doit
    0.83
     in
    0.81
     rush
    0.81
     assist
    0.81
     injunction
    0.80
     to
    0.79
     must
    0.79
     hurry
    0.79
     cannot
    0.78
    POSITIVE LOGITS
    Specifically
    0.85
    Finally
    0.83
    Here
    0.82
    Following
    0.82
     Interestingly
    0.79
    われています
    0.78
    While
    0.78
     Following
    0.77
     Their
    0.77
    ững
    0.77
    Act Density 0.053%

    No Known Activations