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
     말했다
    -0.07
    Cars
    -0.07
    codile
    -0.06
     urn
    -0.06
    sim
    -0.06
     arbitrary
    -0.06
    units
    -0.06
    oured
    -0.06
     Both
    -0.06
    508
    -0.06
    POSITIVE LOGITS
    .On
    0.08
    ={↵
    0.07
    転
    0.07
    .GetInt
    0.07
    нова
    0.06
     Dow
    0.06
     Lifecycle
    0.06
    ritch
    0.06
     khởi
    0.06
     Nab
    0.06
    Act Density 0.000%

    No Known Activations