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

    Neuronpedia

    INDEX
    Explanations

    turn around

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Bah
    -0.08
    upal
    -0.08
     Bah
    -0.08
     Vor
    -0.08
    ÙĪØ°
    -0.08
     PUS
    -0.08
     SF
    -0.08
    UX
    -0.08
    orrent
    -0.08
     Tau
    -0.07
    POSITIVE LOGITS
     turned
    0.53
     turn
    0.51
     turning
    0.46
    turn
    0.43
     turns
    0.42
    turned
    0.41
     Turn
    0.40
     TURN
    0.39
    -turn
    0.38
    Turn
    0.36
    Act Density 0.030%

    No Known Activations