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

    Neuronpedia

    INDEX
    Explanations

    move towards or strategic action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ad
    0.51
    Moving
    0.50
    j
    0.46
     task
    0.44
     moving
    0.43
     Moving
    0.43
    task
    0.43
     Task
    0.42
    moving
    0.41
    ok
    0.41
    POSITIVE LOGITS
     made
    0.54
     applauded
    0.49
     regretted
    0.48
    荥
    0.45
     gemaakt
    0.45
     سوی
    0.44
     estrategia
    0.44
     bylaws
    0.43
    ৈতিক
    0.43
     маъ
    0.42
    Act Density 0.009%

    No Known Activations