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

    Neuronpedia

    INDEX
    Explanations

    code execution context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ين
    0.85
    f
    0.82
    يل
    0.81
    5
    0.80
    q
    0.80
    ٥
    0.79
    لي
    0.78
    ر
    0.78
    r
    0.77
    ه
    0.72
    POSITIVE LOGITS
     Besonder
    0.65
     predicament
    0.60
     Per
    0.59
     slander
    0.55
     statute
    0.54
     tyrant
    0.54
     disbursements
    0.52
     mercenary
    0.52
     bureaucratic
    0.52
     perjury
    0.52
    Act Density 0.001%

    No Known Activations