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

    Neuronpedia

    INDEX
    Explanations

    merge, from, Francis Joseph, Unmyelinated, [An, Electoral

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CARACTERIST
    -1.05
    ėjimas
    -1.04
    服务的
    -1.03
    🫶
    -1.02
    ---
    -1.02
    下一步
    -1.01
    Interess
    -1.01
     denselben
    -0.97
    --$
    -0.95
     volete
    -0.95
    POSITIVE LOGITS
     from
    1.16
     another
    0.98
     and
    0.96
     sœur
    0.94
    wnątrz
    0.93
    PROTE
    0.91
     fellow
    0.90
     [
    0.88
    mergeFrom
    0.88
     Enti
    0.85
    Act Density 0.000%

    No Known Activations