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

    Neuronpedia

    INDEX
    Explanations

    Past-tense suffixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stride
    -0.07
     entrusted
    -0.06
    pections
    -0.06
     describes
    -0.06
     ─
    -0.06
    .lower
    -0.06
    Authority
    -0.06
    /issues
    -0.06
     objeto
    -0.06
    서는
    -0.06
    POSITIVE LOGITS
    始
    0.07
     đạt
    0.06
    ΑΓ
    0.06
    .EventArgs
    0.06
    kově
    0.06
     sci
    0.06
    ジ
    0.06
    HI
    0.06
    .refs
    0.06
    riter
    0.06
    Act Density 0.027%

    No Known Activations