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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ginas
    -0.07
    Come
    -0.06
    ُو
    -0.06
    .key
    -0.06
    bou
    -0.06
     gracious
    -0.06
     Come
    -0.06
    альна
    -0.06
     döneminde
    -0.06
    ighborhood
    -0.05
    POSITIVE LOGITS
    stractions
    0.07
     ###↵
    0.07
    (Config
    0.06
    _wp
    0.06
    (hist
    0.06
    act
    0.06
    erman
    0.06
     ```↵
    0.06
    TN
    0.06
    ])
↵
↵
    0.06
    Act Density 0.016%

    No Known Activations