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

    Neuronpedia

    INDEX
    Explanations

    globe and its associations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    嘛
    0.39
    ieux
    0.39
    rgba
    0.36
    olio
    0.36
    ραγ
    0.36
    llll
    0.35
    solution
    0.35
     Woodford
    0.35
    始
    0.35
    posure
    0.35
    POSITIVE LOGITS
     globe
    0.59
    GLOB
    0.57
     Globe
    0.57
    Glob
    0.57
     glob
    0.56
     Glob
    0.54
    Globe
    0.53
     Globes
    0.52
     GLOB
    0.50
    etrot
    0.48
    Act Density 0.005%

    No Known Activations