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

    Neuronpedia

    INDEX
    Explanations

    pointer reversal and while loops

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Credentials
    0.44
     motorised
    0.42
     reproach
    0.42
     sukces
    0.41
     warmest
    0.40
     remarquer
    0.40
     الشمس
    0.40
     BVHTree
    0.40
     discredited
    0.39
    <unused1067>
    0.39
    POSITIVE LOGITS
     searching
    0.81
     search
    0.68
     mencari
    0.67
    searching
    0.66
    Searching
    0.65
     Searching
    0.63
     investigating
    0.59
     Search
    0.58
    寻找
    0.56
     looking
    0.55
    Act Density 0.000%

    No Known Activations