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

    Neuronpedia

    INDEX
    Explanations

    technical problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    恋
    -0.06
     bb
    -0.06
    ulant
    -0.06
    inement
    -0.06
    跑
    -0.06
    {n
    -0.06
    .deck
    -0.06
    ulously
    -0.06
    lament
    -0.06
    CD
    -0.06
    POSITIVE LOGITS
    _statement
    0.07
     método
    0.07
    Reason
    0.07
    etermination
    0.07
     مج
    0.07
     Bottle
    0.07
    /:
    0.06
    biology
    0.06
    ivar
    0.06
    áveis
    0.06
    Act Density 0.433%

    No Known Activations