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

    Neuronpedia

    INDEX
    Explanations

    quantities and durations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    m
    0.48
    0.46
     Изда
    0.45
    s
    0.44
    ed
    0.44
    filtered
    0.43
     Phoenix
    0.43
    en
    0.43
    ac
    0.42
    er
    0.42
    POSITIVE LOGITS
    邡
    0.61
     agrícola
    0.57
     absenteeism
    0.54
     agrícolas
    0.54
     kuy
    0.53
    រយៈ
    0.53
    Antaeotricha
    0.52
     amelyek
    0.52
     absentee
    0.51
    0.51
    Act Density 0.001%

    No Known Activations