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

    Neuronpedia

    INDEX
    Explanations

    time units and durations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     not
    -1.55
     BaseEntity
    -1.48
    nother
    -1.40
    ufficient
    -1.35
     barva
    -1.33
     from
    -1.31
    ANTES
    -1.30
     bestens
    -1.30
     hitherto
    -1.30
     means
    -1.29
    POSITIVE LOGITS
     даже
    1.77
    }$,
    1.65
     of
    1.61
     gustaba
    1.46
    ми
    1.46
     после
    1.46
     навіть
    1.45
     его
    1.45
     gustó
    1.45
    甚至
    1.42
    Act Density 0.037%

    No Known Activations