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

    Neuronpedia

    INDEX
    Explanations

    vertical transport

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    VIDIA
    0.55
    ol
    0.54
    ប្រ
    0.52
    ൽപ്പന
    0.52
    JScripts
    0.51
    WING
    0.51
    il
    0.50
    isse
    0.49
     Экс
    0.49
     отдельных
    0.48
    POSITIVE LOGITS
     elevator
    0.86
     elevators
    0.85
     Elevator
    0.71
    elevator
    0.64
     escalator
    0.61
    ोड
    0.56
    梯
    0.55
     escalate
    0.55
     stairs
    0.54
     stairway
    0.53
    Act Density 0.004%

    No Known Activations