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

    Neuronpedia

    INDEX
    Explanations

    also lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    又
    0.70
    また
    0.69
     ايضا
    0.68
    加え
    0.67
     également
    0.66
     أيضًا
    0.66
    加えて
    0.63
     hashedPassword
    0.63
    Additional
    0.63
    在
    0.63
    POSITIVE LOGITS
     bukanlah
    0.80
     isn
    0.77
     nėra
    0.74
     necessitates
    0.70
     değildir
    0.69
     isnt
    0.68
     bukan
    0.67
     compromises
    0.66
     disrupts
    0.66
     исключительно
    0.65
    Act Density 0.000%

    No Known Activations