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

    Neuronpedia

    INDEX
    Explanations

    Kir/irs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Sand
    -0.07
    otechnology
    -0.06
    .Nullable
    -0.06
     fetus
    -0.06
     сот
    -0.06
     село
    -0.06
    when
    -0.06
     toen
    -0.06
     Slot
    -0.06
    wolf
    -0.06
    POSITIVE LOGITS
    ir
    0.14
    IR
    0.13
    ira
    0.12
    iri
    0.10
    irs
    0.10
    _IR
    0.10
     IR
    0.09
     lr
    0.09
    IRA
    0.09
    irk
    0.09
    Act Density 0.194%

    No Known Activations