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

    Neuronpedia

    INDEX
    Explanations

    mechanical components and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     draining
    0.69
    Drain
    0.69
     শুন
    0.66
     Drain
    0.66
    torch
    0.65
     demandé
    0.65
    solar
    0.64
     drains
    0.64
     circulatory
    0.64
     peralatan
    0.64
    POSITIVE LOGITS
     actuation
    1.11
     spring
    1.08
     Mechanism
    1.06
     mechanism
    1.05
     click
    1.02
     travel
    0.98
    行程
    0.98
     springs
    0.96
    mechanism
    0.96
     mécanisme
    0.96
    Act Density 0.168%

    No Known Activations