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

    Neuronpedia

    INDEX
    Explanations

    single letters and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     endophytic
    0.20
     intramolecular
    0.19
     imprisoned
    0.19
    renzia
    0.19
    癃
    0.19
     denaturation
    0.19
    沍
    0.19
    GTBase
    0.19
     upregulation
    0.19
     imprisonment
    0.19
    POSITIVE LOGITS
    А
    0.24
    Z
    0.23
    1
    0.22
    if
    0.22
    М
    0.22
    S
    0.22
    C
    0.21
    M
    0.21
    G
    0.20
    N
    0.20
    Act Density 0.329%

    No Known Activations