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

    Neuronpedia

    INDEX
    Explanations

    questions and analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     flamboyant
    1.05
     sentimental
    0.98
     de
    0.98
     sedan
    0.97
     oval
    0.96
     des
    0.96
     den
    0.95
     wearer
    0.94
     ona
    0.93
     fl
    0.93
    POSITIVE LOGITS
    Question
    1.85
    How
    1.78
    Define
    1.76
    Identify
    1.71
    Determine
    1.67
    So
    1.66
    Problem
    1.66
    Consider
    1.63
    Identifying
    1.61
    Q
    1.60
    Act Density 0.000%

    No Known Activations