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

    Neuronpedia

    INDEX
    Explanations

    9

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    нед
    -0.07
    ercise
    -0.07
    بوب
    -0.06
    腿
    -0.06
     damit
    -0.06
     определен
    -0.06
    )i
    -0.06
    ậm
    -0.06
    )e
    -0.06
    geben
    -0.06
    POSITIVE LOGITS
     accession
    0.07
    .Produ
    0.07
     ekonom
    0.07
     AJAX
    0.07
    derived
    0.07
    _BOUND
    0.06
     confidentiality
    0.06
     interview
    0.06
     provincia
    0.06
     PowerPoint
    0.06
    Act Density 0.021%

    No Known Activations