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

    Neuronpedia

    INDEX
    Explanations

    credentials

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    议
    -0.08
     dint
    -0.08
     fren
    -0.08
     collision
    -0.08
    .Coll
    -0.08
     번째
    -0.07
    꾸
    -0.07
     embracing
    -0.07
     강조
    -0.07
     근
    -0.07
    POSITIVE LOGITS
    (credentials
    0.12
     credentials
    0.12
    redentials
    0.11
    credentials
    0.11
    Credentials
    0.11
     Credentials
    0.11
    .credentials
    0.11
     creds
    0.10
    _credentials
    0.10
     વિગતો
    0.09
    Act Density 0.008%

    No Known Activations