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

    Neuronpedia

    INDEX
    Explanations

    internet addresses and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    at
    0.54
    ad
    0.47
    aj
    0.45
    ik
    0.41
    al
    0.38
    ut
    0.36
    ap
    0.35
    ab
    0.35
    ou
    0.34
    af
    0.34
    POSITIVE LOGITS
     as
    0.38
    "
    0.32
    $
    0.30
    ми
    0.30
    G
    0.29
     propriétaire
    0.27
    ო
    0.27
    Ве
    0.26
    לו
    0.26
    ロ
    0.26
    Act Density 0.000%

    No Known Activations