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

    Neuronpedia

    INDEX
    Explanations

    such

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    810
    -0.07
    .enter
    -0.07
     Orlando
    -0.06
     Monad
    -0.06
     intro
    -0.06
     Jordan
    -0.06
    _OR
    -0.06
     went
    -0.06
     Electron
    -0.06
    orrent
    -0.06
    POSITIVE LOGITS
     machinery
    0.07
     USC
    0.07
    US
    0.07
     architects
    0.07
     douche
    0.07
    -redux
    0.07
     systém
    0.07
     شه
    0.07
    [hash
    0.07
     architect
    0.07
    Act Density 0.074%

    No Known Activations