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

    Neuronpedia

    INDEX
    Explanations

    implants

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     questionable
    -0.07
     Window
    -0.06
    253
    -0.06
     rectangular
    -0.06
    78
    -0.06
     festival
    -0.06
    Pipeline
    -0.06
     window
    -0.06
     revenue
    -0.06
    Cr
    -0.06
    POSITIVE LOGITS
     implants
    0.25
    plants
    0.09
     gösterir
    0.08
                      ↵
    0.07
     ]);↵↵
    0.07
    ovan
    0.06
    خم
    0.06
    lients
    0.06
    SPA
    0.06
    .fold
    0.06
    Act Density 0.001%

    No Known Activations