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

    Neuronpedia

    INDEX
    Explanations

    limit to one or only

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    囪
    0.39
     pro
    0.38
     extras
    0.37
     bicicleta
    0.37
     lateral
    0.37
     pointwise
    0.36
     safe
    0.36
     በእ
    0.35
    枉
    0.35
     Det
    0.35
    POSITIVE LOGITS
     član
    0.53
    members
    0.52
    สมาชิก
    0.52
     medlem
    0.50
    Members
    0.50
    member
    0.49
     Mitglied
    0.49
    成员
    0.47
     Mitglieder
    0.47
     सदस्यों
    0.46
    Act Density 0.000%

    No Known Activations