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
     metrics
    -0.07
    [num
    -0.07
    /location
    -0.07
    储备
    -0.07
    (groups
    -0.07
    wealth
    -0.07
     (“
    -0.07
    vy
    -0.06
    .Today
    -0.06
     noted
    -0.06
    POSITIVE LOGITS
    選�
    0.07
     portraits
    0.07
     CURL
    0.07
     produtos
    0.07
     IHttpActionResult
    0.07
     when
    0.07
     Jahr
    0.07
     życie
    0.07
    indo
    0.07
     yüzden
    0.07
    Act Density 0.003%

    No Known Activations