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

    Neuronpedia

    INDEX
    Explanations

    note, disclaimer, requires, important

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Prague
    0.42
     pioneering
    0.38
    一颗
    0.38
     THAT
    0.38
     itemView
    0.38
    枫
    0.38
     stars
    0.38
     można
    0.37
    നം
    0.37
     vol
    0.36
    POSITIVE LOGITS
    gres
    0.50
    pym
    0.43
    matched
    0.42
    isp
    0.41
     &=
    0.41
    醤
    0.41
    стые
    0.40
    pyridine
    0.40
    Python
    0.39
     matched
    0.39
    Act Density 0.000%

    No Known Activations