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

    Neuronpedia

    INDEX
    Explanations

    starts questions or requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     รวม
    0.34
    ),
    0.33
     ||
    0.33
    といった
    0.32
    })
    0.32
    built
    0.32
     callous
    0.32
     รวมถึง
    0.31
     interne
    0.30
    ())
    0.30
    POSITIVE LOGITS
     букмекерлар
    0.39
     mujhe
    0.38
    邀请
    0.36
     کیسینو
    0.36
     midfielder
    0.36
    私は
    0.35
     मुस्लिम
    0.35
     refinancing
    0.34
     lesbian
    0.34
     Cryptocurrency
    0.34
    Act Density 6.214%

    No Known Activations