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

    Neuronpedia

    INDEX
    Explanations

    closing parenthesis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    1.06
     （
    0.64
    (
    0.64
     ("
    0.63
     ((
    0.61
    （
    0.59
     be
    0.57
     pés
    0.57
     (<
    0.52
    S
    0.52
    POSITIVE LOGITS
    hos
    0.64
    ahh
    0.57
    ో
    0.56
    ा
    0.56
    া
    0.55
    ষধ
    0.54
    രുവന
    0.54
    eers
    0.54
    harth
    0.53
     እና
    0.52
    Act Density 0.152%

    No Known Activations