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

    Neuronpedia

    INDEX
    Explanations

    programmers `init`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.81
    us
    0.67
    DriverManager
    0.57
    galo
    0.56
    ligence
    0.56
    که
    0.54
    ren
    0.52
     новых
    0.52
    ेस
    0.51
    phan
    0.50
    POSITIVE LOGITS
    ");
    0.62
     Seite
    0.57
     twor
    0.56
    ير
    0.55
     would
    0.53
     שני
    0.53
     Shrimp
    0.52
     R
    0.50
    Ẻ
    0.50
     descend
    0.50
    Act Density 0.000%

    No Known Activations