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

    Neuronpedia

    INDEX
    Explanations

    right now

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     سلم
    0.74
    Self
    0.72
    Weeks
    0.68
     Weeks
    0.68
     Side
    0.68
    DataFrame
    0.68
    Sides
    0.67
    Backward
    0.65
    Escape
    0.65
     Self
    0.65
    POSITIVE LOGITS
    ically
    0.91
     dove
    0.84
     troopers
    0.82
    jetas
    0.82
     arriba
    0.81
     hacker
    0.81
     attorno
    0.80
     dhatu
    0.79
     enlisted
    0.78
     ahead
    0.77
    Act Density 0.082%

    No Known Activations