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

    Neuronpedia

    INDEX
    Explanations

    transform position

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    alignat
    0.40
     capital
    0.38
     isothermal
    0.37
    <unused68>
    0.36
    तोंडा
    0.36
    颏
    0.36
     monstrous
    0.36
     watches
    0.35
     बरकरार
    0.35
     cones
    0.35
    POSITIVE LOGITS
    position
    0.54
     position
    0.46
    Position
    0.42
     document
    0.39
     Position
    0.39
    位置
    0.37
     документ
    0.37
    Deep
    0.37
    Contributions
    0.37
    dire
    0.36
    Act Density 0.001%

    No Known Activations