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

    Neuronpedia

    INDEX
    Explanations

    aunt followed by a name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     istanbul
    0.39
    请求
    0.38
     fc
    0.38
    שת
    0.38
    Amit
    0.38
     parturient
    0.37
    まち
    0.37
     porcentaje
    0.36
     mari
    0.36
    ittha
    0.36
    POSITIVE LOGITS
     L
    0.71
     Julia
    0.68
    Julia
    0.64
     jul
    0.55
    jul
    0.55
    L
    0.51
    JUL
    0.50
     Jul
    0.50
     Julian
    0.50
     JUL
    0.50
    Act Density 0.000%

    No Known Activations