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

    Neuronpedia

    INDEX
    Explanations

    descriptive words followed by related nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     reperc
    -0.10
    654
    -0.09
    .Excel
    -0.09
     spawns
    -0.09
    539
    -0.08
    HECK
    -0.08
    tainment
    -0.08
    еÑĢж
    -0.08
     pedest
    -0.08
    heimer
    -0.08
    POSITIVE LOGITS
    kee
    0.10
    lev
    0.09
    i
    0.09
     airl
    0.09
    oc
    0.09
     accounting
    0.09
    unden
    0.08
     enterprises
    0.08
    âħ¥
    0.08
     ske
    0.08
    Act Density 0.060%

    No Known Activations