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

    Neuronpedia

    INDEX
    Explanations

    shift control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    翾
    -1.05
    髕
    -1.05
     kematian
    -0.99
    鸶
    -0.98
     їх
    -0.96
     importación
    -0.93
    ثمار
    -0.93
     ANIMAL
    -0.91
    慙
    -0.91
    pkins
    -0.91
    POSITIVE LOGITS
     Shift
    1.76
     shift
    1.63
     Shifting
    1.59
     shifts
    1.46
    Shift
    1.46
     SH
    1.44
     SHIFT
    1.39
    SHIFT
    1.38
    hift
    1.36
     Shi
    1.26
    Act Density 0.012%

    No Known Activations