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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     opposition
    -0.28
    isan
    -0.26
    anja
    -0.26
    >Lorem
    -0.25
    å±ı
    -0.25
    rema
    -0.25
    onga
    -0.24
     Lorem
    -0.24
    renc
    -0.24
    glas
    -0.24
    POSITIVE LOGITS
     conv
    0.29
    .Empty
    0.29
     Intent
    0.28
     Polo
    0.28
    iken
    0.27
    ä¾Ŀæį®
    0.26
     spa
    0.26
     invoke
    0.26
     ug
    0.26
    å¤©åľ°
    0.26
    Act Density 0.030%

    No Known Activations