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

    Neuronpedia

    INDEX
    Explanations

    classic theories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    घात
    0.42
    ત્
    0.40
     malla
    0.39
     संघा
    0.39
     presentar
    0.38
    Presented
    0.38
     تاکہ
    0.38
    Payroll
    0.38
    Hari
    0.38
     사실
    0.38
    POSITIVE LOGITS
     occasionally
    0.38
    .]
    0.37
     CCc
    0.37
    тится
    0.37
    uğ
    0.37
    asctime
    0.36
     Occasionally
    0.35
    .*
    0.35
     Temperatures
    0.35
     temperatures
    0.34
    Act Density 0.002%

    No Known Activations