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

    Neuronpedia

    INDEX
    Explanations

    time expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     celebración
    0.52
     geleden
    0.52
     passada
    0.48
    📆
    0.48
     itib
    0.48
    🗓
    0.47
     háb
    0.47
    ✈
    0.45
     écoul
    0.45
    आन
    0.45
    POSITIVE LOGITS
     momentary
    0.52
     algorithm
    0.52
     syntax
    0.47
     instantiation
    0.47
     code
    0.46
    _
    0.46
     numpy
    0.46
     computationally
    0.46
     metadata
    0.45
     path
    0.45
    Act Density 0.094%

    No Known Activations