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

    Neuronpedia

    INDEX
    Explanations

    comport behavior

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    د
    1.52
    us
    1.13
    ون
    1.05
    dienst
    0.99
     as
    0.98
    ৫
    0.98
    in
    0.93
    śmy
    0.93
    טן
    0.92
    al
    0.91
    POSITIVE LOGITS
     an
    1.52
    Р
    1.19
    u
    1.14
    을
    1.02
    you
    0.99
    R
    0.98
    О
    0.96
    ార్
    0.95
    이
    0.94
     you
    0.93
    Act Density 0.000%

    No Known Activations