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

    Neuronpedia

    INDEX
    Explanations

    html head meta tag

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Antae
    0.37
     leapt
    0.37
     montagnes
    0.36
    MOUNTAINS
    0.36
    ವಿಧ
    0.36
    Multicolored
    0.36
     mocy
    0.36
    Concini
    0.35
    sensing
    0.35
    প্তি
    0.35
    POSITIVE LOGITS
     Ret
    0.38
     March
    0.36
     Meta
    0.34
    name
    0.33
     கல்
    0.33
    Ret
    0.33
     Neo
    0.32
     Cast
    0.31
     American
    0.31
     Retail
    0.31
    Act Density 0.001%

    No Known Activations