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

    Neuronpedia

    INDEX
    Explanations

    numbers after code and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ach
    0.99
    better
    0.98
    analog
    0.98
    哧
    0.90
    }},
    0.90
    Allow
    0.89
    Michael
    0.87
     tyto
    0.87
    }$)
    0.86
     लिये
    0.85
    POSITIVE LOGITS
     धावा
    1.12
    қу
    1.07
     Smoothing
    1.04
     criticality
    1.02
     melts
    1.02
     warmup
    1.02
     Hadid
    1.01
     sogg
    1.01
    1.01
     begun
    1.00
    Act Density 0.023%

    No Known Activations