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

    Neuronpedia

    INDEX
    Explanations

    confined

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     glyphicon
    -0.07
    /Subthreshold
    -0.07
    _spinner
    -0.06
     ягод
    -0.06
    ?>">
    -0.06
    SEQUENTIAL
    -0.06
    ?>"><
    -0.06
     Marketplace
    -0.06
    succ
    -0.06
     дорож
    -0.06
    POSITIVE LOGITS
     confined
    0.17
     confinement
    0.14
     confines
    0.11
    hf
    0.08
     constrain
    0.07
     Kim
    0.07
    fine
    0.07
     inmate
    0.07
    mine
    0.07
     kid
    0.07
    Act Density 0.002%

    No Known Activations