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

    Neuronpedia

    INDEX
    Explanations

    directions to navigate or go

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ch
    1.10
    le
    0.90
     colon
    0.82
    From
    0.82
    a
    0.80
    na
    0.79
    lee
    0.78
    za
    0.78
    d
    0.77
     frame
    0.76
    POSITIVE LOGITS
    Ꮬ
    1.37
    <unused930>
    1.29
     във
    1.20
     coalgebras
    1.20
    дің
    1.20
    дың
    1.20
    ⎣
    1.17
    <unused1223>
    1.16
    <unused1827>
    1.15
     äußerst
    1.14
    Act Density 0.001%

    No Known Activations