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

    Neuronpedia

    INDEX
    Explanations

    frequency

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -Origin
    -0.08
    .dict
    -0.07
     unethical
    -0.07
    aigned
    -0.06
    DataProvider
    -0.06
     Basically
    -0.06
    getConnection
    -0.06
    restaurant
    -0.06
    .EVENT
    -0.06
    .Intent
    -0.06
    POSITIVE LOGITS
     Kubernetes
    0.08
     single
    0.07
    andelier
    0.07
     خدا
    0.07
     INF
    0.06
    /gen
    0.06
     VLC
    0.06
     morb
    0.06
    embre
    0.06
     bánh
    0.06
    Act Density 0.001%

    No Known Activations