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

    Neuronpedia

    INDEX
    Explanations

    authors and historical figures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tarantino
    0.42
    Etiam
    0.41
    𝗔
    0.40
    吲
    0.38
    ⃞
    0.37
    Sensitivity
    0.37
    ☠
    0.37
    Assignment
    0.36
    睞
    0.36
    "${
    0.36
    POSITIVE LOGITS
     London
    0.46
     Henry
    0.42
     Percy
    0.42
     British
    0.38
     vols
    0.38
     Ruskin
    0.38
     published
    0.38
     nineteenth
    0.38
    英国
    0.38
     Victorian
    0.38
    Act Density 0.004%

    No Known Activations