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

    Neuronpedia

    INDEX
    Explanations

    mass

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mid
    -0.06
     αρχ
    -0.06
    	z
    -0.06
    _ptrs
    -0.06
     cores
    -0.06
     animations
    -0.06
    ีซ
    -0.06
    MODE
    -0.06
     lk
    -0.06
    travel
    -0.06
    POSITIVE LOGITS
     mastering
    0.08
    ницип
    0.08
     primaryStage
    0.07
     Merlin
    0.07
    ↵↵↵↵↵↵
    0.06
     Cobb
    0.06
    (provider
    0.06
                  ↵
    0.06
     �
    0.06
    _modules
    0.06
    Act Density 0.061%

    No Known Activations