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

    Neuronpedia

    INDEX
    Explanations

    -->

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ordin
    -0.07
    ht
    -0.07
    appId
    -0.07
     plumbing
    -0.07
    th
    -0.06
    _ns
    -0.06
    (out
    -0.06
     machining
    -0.06
     badge
    -0.06
    xeb
    -0.06
    POSITIVE LOGITS
     Appears
    0.07
     erotica
    0.07
    cerr
    0.07
     serta
    0.07
     mực
    0.07
    -->↵
    0.07
    -American
    0.07
     Teuchos
    0.07
     önemlidir
    0.07
     click
    0.07
    Act Density 0.003%

    No Known Activations