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

    Neuronpedia

    INDEX
    Explanations

    significance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Boss
    -0.07
    [frame
    -0.07
     Iceland
    -0.06
     Fischer
    -0.06
     Moodle
    -0.06
     FPS
    -0.06
    eng
    -0.06
    После
    -0.06
    ись
    -0.06
     performer
    -0.06
    POSITIVE LOGITS
     pir
    0.08
    नल
    0.07
    (border
    0.06
     отк
    0.06
     ARR
    0.06
     PY
    0.06
     cam
    0.06
     arising
    0.06
     البحر
    0.06
     ऐ
    0.06
    Act Density 0.038%

    No Known Activations