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

    Neuronpedia

    INDEX
    Explanations

    meal times and plans

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tempor
    0.38
     Tempor
    0.37
    Genuine
    0.36
     lens
    0.34
     disinformation
    0.34
     undergraduate
    0.34
     coworker
    0.34
    andus
    0.34
     waxes
    0.34
     distrust
    0.33
    POSITIVE LOGITS
     break
    0.69
     snacks
    0.64
     served
    0.64
    🍴
    0.63
     ब्रेक
    0.62
    🍽
    0.62
     eaten
    0.61
     Break
    0.59
    🍱
    0.59
     overlooking
    0.58
    Act Density 0.024%

    No Known Activations