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

    Neuronpedia

    INDEX
    Explanations

    word endings on/ron/ton

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ieve
    -0.08
    omaly
    -0.07
     เค
    -0.07
    eníze
    -0.07
    are
    -0.07
    1
    -0.07
    ellite
    -0.07
    +E
    -0.07
    name
    -0.07
    (E
    -0.07
    POSITIVE LOGITS
    on
    0.16
    ON
    0.15
    son
    0.12
    ton
    0.11
    gon
    0.11
    SON
    0.10
    он
    0.10
    sson
    0.10
    aton
    0.10
    bon
    0.09
    Act Density 0.225%

    No Known Activations