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

    Neuronpedia

    INDEX
    Explanations

    fitting in, suitability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tic
    1.09
     countable
    1.08
    ره
    1.08
    igenschaften
    1.05
    ة
    1.04
    PF
    1.01
    tive
    1.01
    归
    1.01
    वृद्धि
    1.00
    ई
    0.99
    POSITIVE LOGITS
     snugly
    2.37
     snug
    1.34
    spiration
    1.29
    জিওথের
    1.23
    ſelf
    1.19
    adino
    1.18
     comfortably
    1.13
    д
    1.12
     uncl
    1.10
     बैठ
    1.09
    Act Density 0.061%

    No Known Activations