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

    Neuronpedia

    INDEX
    Explanations

    time with pm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    xy
    0.60
     exploitation
    0.59
    ichte
    0.57
     finite
    0.57
    ulence
    0.57
     dielectric
    0.57
    oteric
    0.57
    exploitation
    0.57
     subset
    0.55
     original
    0.54
    POSITIVE LOGITS
    pm
    1.77
     noon
    1.76
     pm
    1.75
     Afternoon
    1.65
     Noon
    1.64
     afternoon
    1.60
     बजे
    1.56
     PM
    1.49
    PM
    1.46
     lunchtime
    1.42
    Act Density 0.175%

    No Known Activations