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

    Neuronpedia

    INDEX
    Explanations

    unfortunate events and their aftermath

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     آماده
    0.82
     thereafter
    0.81
     afterward
    0.81
     once
    0.81
     afterwards
    0.77
     everywhere
    0.77
     lately
    0.75
     throughout
    0.74
    after
    0.73
     after
    0.73
    POSITIVE LOGITS
     LESS
    0.73
     Less
    0.71
     assisted
    0.68
    Less
    0.67
     který
    0.67
    minutes
    0.65
     который
    0.64
     less
    0.63
    less
    0.63
     minutes
    0.62
    Act Density 0.114%

    No Known Activations