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

    Neuronpedia

    INDEX
    Explanations

    out, up, down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bl
    0.18
    وظ
    0.18
    つの
    0.17
    ване
    0.17
    dés
    0.17
     सॉल्यू
    0.17
     مہ
    0.17
    資産
    0.16
    पण
    0.16
     medlem
    0.16
    POSITIVE LOGITS
     into
    0.29
    WARDS
    0.26
     onto
    0.26
     from
    0.24
     with
    0.23
     to
    0.21
     on
    0.20
     grasping
    0.20
     अनुभ
    0.20
    㚼
    0.19
    Act Density 0.050%

    No Known Activations