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

    Neuronpedia

    INDEX
    Explanations

    Detroit city and its associations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0
    2.27
    ות
    1.63
    ０
    1.34
     by
    1.31
     for
    1.28
     as
    1.26
    u
    1.26
    ן
    1.22
     but
    1.21
     from
    1.20
    POSITIVE LOGITS
    ل
    1.08
    ल
    0.98
     Detroit
    0.97
    ל
    0.96
    Det
    0.94
    しっかりと
    0.93
    म
    0.93
    욌
    0.92
    ren
    0.92
    м
    0.92
    Act Density 0.006%

    No Known Activations