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

    Neuronpedia

    INDEX
    Explanations

    movement and direction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Lookup
    0.48
    Crash
    0.48
    Heart
    0.47
    Flow
    0.47
    Fine
    0.46
    וני
    0.46
     נ
    0.46
    Iter
    0.45
    valid
    0.45
    לב
    0.45
    POSITIVE LOGITS
     away
    1.50
     out
    1.22
     into
    1.22
     towards
    1.16
     off
    1.12
     toward
    1.12
     forward
    1.07
     outwards
    1.05
     inwards
    1.04
     down
    1.04
    Act Density 0.407%

    No Known Activations