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

    Neuronpedia

    INDEX
    Explanations

    my, your, his, their, its

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    že
    0.42
    in
    0.42
     অনুরোধ
    0.38
     για
    0.37
    ak
    0.37
     для
    0.36
    ley
    0.36
    ți
    0.36
     bijna
    0.35
     போட்டி
    0.35
    POSITIVE LOGITS
    0.55
     is
    0.37
    INY
    0.35
    <
    0.34
    ENT
    0.34
    Impl
    0.34
    Statistic
    0.34
     of
    0.33
    Episode
    0.32
    Calculation
    0.32
    Act Density 0.314%

    No Known Activations