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

    Neuronpedia

    INDEX
    Explanations

    stop or station

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ஜித்
    0.42
     ईमान
    0.40
    Occupation
    0.39
     sobr
    0.39
    褔
    0.38
    javaHome
    0.38
    🕵
    0.38
    的表现
    0.37
    谋
    0.37
     অস্ব
    0.37
    POSITIVE LOGITS
     stops
    1.13
    stops
    1.00
     destination
    0.99
     destinations
    0.99
     stopping
    0.99
     terminus
    0.96
     stop
    0.92
     unloading
    0.91
     terminal
    0.90
    destination
    0.88
    Act Density 0.013%

    No Known Activations