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

    Neuronpedia

    INDEX
    Explanations

    processes and workflows

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ih
    -0.07
     Tus
    -0.06
     içi
    -0.06
     patt
    -0.06
    .toolStripSeparator
    -0.06
     confort
    -0.06
    icionar
    -0.06
     threesome
    -0.06
     duro
    -0.06
    <message
    -0.06
    POSITIVE LOGITS
    AMP
    0.07
    employed
    0.07
     supply
    0.07
     Destroy
    0.07
    م
    0.06
    енном
    0.06
    abis
    0.06
    MA
    0.06
     entitlement
    0.06
     jednak
    0.06
    Act Density 0.296%

    No Known Activations